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

    Neuronpedia

    INDEX
    Explanations

    references to legal and judicial processes

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

    Tokens appearing after certain words/phrases

    np_acts-logits-general · gemini-2.0-flash

    reject or overturn

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    webElementXpaths
    -0.41
     rajut
    -0.41
    fiehlt
    -0.37
     dogmatic
    -0.37
    omiast
    -0.35
     conversación
    -0.35
     köpek
    -0.35
     headsets
    -0.35
     verantwort
    -0.35
    Cordialement
    -0.35
    POSITIVE LOGITS
     nakalista
    0.56
     rebellious
    0.51
    awaiter
    0.50
     rebel
    0.50
     defaultstate
    0.49
    parsedMessage
    0.49
     nahilalakip
    0.48
     Reject
    0.48
     EClass
    0.48
    rebel
    0.47
    Act Density 0.731%

    No Known Activations