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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks within text

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

    Followed by coordinating conjunction

    np_acts-logits-general · gemini-2.0-flash

    linking clauses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     syl
    -0.57
     deb
    -0.51
    istream
    -0.50
     teg
    -0.49
     absc
    -0.48
    fras
    -0.48
     alu
    -0.47
    rager
    -0.47
     sb
    -0.46
     aster
    -0.46
    POSITIVE LOGITS
     informée
    0.62
     humanidade
    0.57
     normalidad
    0.56
     lantaran
    0.55
     comigo
    0.54
     Italij
    0.53
     mercancías
    0.52
     amizade
    0.50
     venganza
    0.50
    Sklici
    0.50
    Act Density 0.549%

    No Known Activations