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

    Neuronpedia

    INDEX
    Explanations

    components

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    287
    -0.06
    목
    -0.06
     eig
    -0.06
    業
    -0.06
     intervals
    -0.06
     чт
    -0.06
     <<<
    -0.05
    Wonder
    -0.05
    屋
    -0.05
     Own
    -0.05
    POSITIVE LOGITS
     savaş
    0.07
     Bolshevik
    0.07
    openhagen
    0.07
     accordingly
    0.07
    ustering
    0.07
    sınız
    0.07
    _ASSOC
    0.07
    PopMatrix
    0.07
     Marian
    0.07
     NAFTA
    0.07
    Act Density 0.090%

    No Known Activations