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

    Neuronpedia

    INDEX
    Explanations

    4

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    77
    -0.08
    66
    -0.07
    (hist
    -0.07
    252
    -0.07
    6
    -0.07
    (serial
    -0.07
    72
    -0.07
    282
    -0.07
    27
    -0.06
     wen
    -0.06
    POSITIVE LOGITS
    PA
    0.08
     policymakers
    0.07
    fdb
    0.07
     USC
    0.07
    历
    0.07
    CA
    0.07
     Erica
    0.07
    Stock
    0.07
    =========↵
    0.06
    c
    0.06
    Act Density 0.025%

    No Known Activations