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

    Neuronpedia

    INDEX
    Explanations

    stylesheet

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     postseason
    -0.06
     bz
    -0.06
     товарів
    -0.06
     真
    -0.06
    ари
    -0.06
     BOOLEAN
    -0.06
     tariff
    -0.06
    .BOTTOM
    -0.06
     Lamar
    -0.06
    chang
    -0.06
    POSITIVE LOGITS
     stone
    0.07
     slaves
    0.06
     subscriptions
    0.06
     desperately
    0.06
    ulsion
    0.06
     Fashion
    0.06
    uellement
    0.06
    远
    0.06
     Hilfe
    0.06
    VENT
    0.06
    Act Density 0.008%

    No Known Activations