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

    Neuronpedia

    INDEX
    Explanations

    Capacity descriptions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    CLK
    -0.08
    December
    -0.07
    decrypt
    -0.06
     Nationals
    -0.06
    /item
    -0.06
    uenta
    -0.06
     которая
    -0.06
     Yard
    -0.06
    ulumi
    -0.06
     Osc
    -0.06
    POSITIVE LOGITS
     persecuted
    0.07
     догов
    0.06
    umin
    0.06
    ิตภ
    0.06
    -describedby
    0.06
    اضي
    0.06
     ประเทศ
    0.06
     کسب
    0.06
     pca
    0.05
     nécess
    0.05
    Act Density 0.129%

    No Known Activations