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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and formulas

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

    Mathematical or physics notation

    np_acts-logits-general · gemini-2.0-flash

    mathematical symbols and foreign words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     LR
    -0.65
    LR
    -0.61
     $\
    -0.60
    cias
    -0.59
     SS
    -0.58
     שוליים
    -0.58
    SS
    -0.56
     JR
    -0.56
     PCP
    -0.55
    YY
    -0.55
    POSITIVE LOGITS
    MigrationBuilder
    0.74
     dignité
    0.64
     speranza
    0.61
     hänen
    0.60
    yntaxException
    0.60
     inconn
    0.58
     étoient
    0.57
     avoient
    0.56
     marquées
    0.56
     rempliss
    0.56
    Act Density 1.289%

    No Known Activations