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

    Neuronpedia

    INDEX
    Explanations

    time

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     boobs
    -0.07
     Revolution
    -0.06
     CART
    -0.06
     myster
    -0.06
    enemy
    -0.06
    grand
    -0.06
     Fathers
    -0.06
    Room
    -0.06
    %!
    -0.06
     Mathematic
    -0.06
    POSITIVE LOGITS
     الظ
    0.07
    .p
    0.06
     bk
    0.06
     Pro
    0.06
    yp
    0.06
    .handleError
    0.06
     intrigue
    0.06
    (callback
    0.06
    =t
    0.06
    populate
    0.06
    Act Density 0.021%

    No Known Activations