Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    comparative adjectives and phrases related to evaluations or assessments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Followed by nouns

    np_acts-logits-general · gemini-2.0-flash

    check, answer, recovery, appeal, association, determination, investigation, invitation, connection

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     الرياضيه
    -0.55
     Nego
    -0.54
     Evalu
    -0.51
    Gön
    -0.50
    ApplicationTests
    -0.50
    WireFormatLite
    -0.50
     Releases
    -0.48
    releases
    -0.48
     replying
    -0.47
    devi
    -0.47
    POSITIVE LOGITS
     betweenstory
    0.86
     financière
    0.69
    expandindo
    0.67
     récentes
    0.66
     démocr
    0.65
     financières
    0.63
    ]]
    0.63
     devriez
    0.63
     vectorielles
    0.63
     flesta
    0.62
    Act Density 1.130%

    No Known Activations