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

    Neuronpedia

    INDEX
    Explanations

    negation phrases

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

    not followed by verb

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Armand
    -0.67
     KGB
    -0.63
    Armand
    -0.62
     Tübingen
    -0.57
    áska
    -0.57
     radia
    -0.56
    XXIII
    -0.56
    erba
    -0.55
    es
    -0.55
     Ibarra
    -0.55
    POSITIVE LOGITS
     Normdatei
    0.96
    CppMethod
    0.95
    VIAF
    0.83
     NOT
    0.82
    MLLoader
    0.81
     Not
    0.77
     <=",
    0.77
    parsedMessage
    0.77
     חיצוניים
    0.76
    ValueStyle
    0.74
    Act Density 0.163%

    No Known Activations