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

    Neuronpedia

    INDEX
    Explanations

    notational symbols and mathematical expressions

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

    Oui

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AnimationsModule
    -0.52
     zijne
    -0.52
     chrétien
    -0.51
     tenisky
    -0.50
    cultural
    -0.50
     ogrodow
    -0.49
     nødven
    -0.48
     inconnu
    -0.46
    CppMethod
    -0.46
     recevez
    -0.45
    POSITIVE LOGITS
    </h5>
    1.86
    <h5>
    0.90
    ']
    0.79
    '];
    0.79
    ']:
    0.76
    '];
    0.75
    〕
    0.74
     **/
    0.74
    </s>
    0.73
    ']]
    0.73
    Act Density 0.001%

    No Known Activations