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

    Neuronpedia

    INDEX
    Explanations

    things

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     centroids
    -0.06
    ูด
    -0.06
    τής
    -0.06
    acked
    -0.06
    bias
    -0.06
    力的
    -0.06
    cdf
    -0.06
    ınızı
    -0.06
    本
    -0.06
    ]},
    -0.06
    POSITIVE LOGITS
     Exercise
    0.07
    companyId
    0.07
    Ag
    0.06
     DataTable
    0.06
     anal
    0.06
    JSONException
    0.06
    verage
    0.06
     kỹ
    0.06
     Rochester
    0.06
    experiment
    0.06
    Act Density 0.007%

    No Known Activations