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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _FIRE
    -0.07
    emaakt
    -0.06
    router
    -0.06
    USE
    -0.06
    Domains
    -0.06
     ω
    -0.06
    �
    -0.06
    aaaa
    -0.06
    ãng
    -0.06
    ático
    -0.06
    POSITIVE LOGITS
     beverage
    0.08
    地
    0.07
    .setStyle
    0.07
     jednodu
    0.06
    extField
    0.06
     graz
    0.06
    /pay
    0.06
     sucking
    0.06
    hope
    0.06
     了
    0.06
    Act Density 0.012%

    No Known Activations