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

    Neuronpedia

    INDEX
    Explanations

    Sizes (76, 40, 60)

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     afternoon
    -0.08
     TIME
    -0.07
     tangent
    -0.07
    	Time
    -0.07
    $/,↵
    -0.06
     might
    -0.06
    oliday
    -0.06
     #{
    -0.06
     IPPROTO
    -0.06
    ıf
    -0.06
    POSITIVE LOGITS
    ！
    0.07
    서
    0.06
    都是
    0.06
    .Throws
    0.06
    自分
    0.06
    _align
    0.06
     sám
    0.06
    哭
    0.06
    (side
    0.06
    ’te
    0.05
    Act Density 0.002%

    No Known Activations