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

    Neuronpedia

    INDEX
    Explanations

    references to speculation, conjecture, and unsupported claims in discussions

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

    unsubstantiated claims and speculation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AutoField
    -0.57
    ThroughAttribute
    -0.55
     الحره
    -0.47
    ActionCreators
    -0.42
    Xna
    -0.42
    NewUrlParser
    -0.42
     INTERESAR
    -0.41
    Географи
    -0.41
    IsMutable
    -0.41
     strip
    -0.39
    POSITIVE LOGITS
     guesses
    0.62
    guesses
    0.57
    guess
    0.56
    jecture
    0.52
     conjecture
    0.52
     guessing
    0.51
     conjectures
    0.50
     speculation
    0.48
     guess
    0.48
    tidumbre
    0.45
    Act Density 0.383%

    No Known Activations