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

    Neuronpedia

    INDEX
    Explanations

    sans

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     bank
    -0.06
    mart
    -0.06
    heads
    -0.06
    иплом
    -0.06
     founder
    -0.06
    conc
    -0.06
    umn
    -0.06
    раб
    -0.06
     His
    -0.06
    rams
    -0.06
    POSITIVE LOGITS
    ponses
    0.06
    (SDL
    0.06
    _tt
    0.06
     الاخ
    0.06
    ROLE
    0.06
    /*↵
    0.06
     Palin
    0.06
     REQUEST
    0.06
     OutputStream
    0.06
     salesman
    0.06
    Act Density 0.001%

    No Known Activations