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

    Neuronpedia

    INDEX
    Explanations

    court documents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    pt
    -0.08
    去掉
    -0.07
    /assets
    -0.07
    <x
    -0.07
     uncertainty
    -0.07
    TextColor
    -0.07
    Typed
    -0.07
     Ricky
    -0.07
     Aspen
    -0.07
     접근
    -0.06
    POSITIVE LOGITS
    ᾳ
    0.08
     mük
    0.07
    😏
    0.07
    croft
    0.07
    здание
    0.06
    �
    0.06
    hawk
    0.06
    ilitary
    0.06
     BK
    0.06
     rail
    0.06
    Act Density 0.004%

    No Known Activations