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

    Neuronpedia

    INDEX
    Explanations

    surprisingly complex topics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    пти
    0.41
     luego
    0.39
    WebRequest
    0.37
     nouve
    0.35
     shaw
    0.35
     guilds
    0.35
    փ
    0.35
    ificados
    0.35
    ShowWindow
    0.35
    सर्व
    0.34
    POSITIVE LOGITS
    一下子
    0.46
    correctAns
    0.46
    iciais
    0.42
     toxicants
    0.41
    NameTo
    0.40
    toxicity
    0.40
     অসুবিধা
    0.40
     विषा
    0.40
     mož
    0.39
     Merck
    0.39
    Act Density 0.000%

    No Known Activations