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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Dudley
    -0.07
     DETAILS
    -0.07
     Kathy
    -0.07
     Account
    -0.06
    ']*
    -0.06
     servisi
    -0.06
     ملت
    -0.06
     Jeff
    -0.06
     christ
    -0.06
     dagger
    -0.06
    POSITIVE LOGITS
    .Res
    0.06
    upplier
    0.06
    旅
    0.06
    粒
    0.06
    าซ
    0.06
     comedian
    0.06
     embody
    0.06
    蒙
    0.06
    _returns
    0.06
    /xml
    0.05
    Act Density 0.000%

    No Known Activations