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

    Neuronpedia

    INDEX
    Explanations

    science and cancer

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     upload
    -0.08
    ombine
    -0.07
     magnet
    -0.07
     subtotal
    -0.06
     positions
    -0.06
    ursors
    -0.06
    以下
    -0.06
     killer
    -0.06
    manent
    -0.06
    IRE
    -0.06
    POSITIVE LOGITS
     نفت
    0.07
     Cone
    0.07
    (repository
    0.07
    cilik
    0.06
    jpg
    0.06
     obrov
    0.06
     Đông
    0.06
    (fabs
    0.06
    하나
    0.06
     fuck
    0.06
    Act Density 0.051%

    No Known Activations