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

    Neuronpedia

    INDEX
    Explanations

    call

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ').
    -0.07
    (T
    -0.07
    ('&
    -0.07
    (side
    -0.06
    -0.06
    /*.
    -0.06
     价格
    -0.06
    .one
    -0.06
    ('${
    -0.06
    (It
    -0.06
    POSITIVE LOGITS
     dolor
    0.07
     dib
    0.06
    pecial
    0.06
     primal
    0.06
     Scandin
    0.06
     дал
    0.06
     début
    0.06
     шляхом
    0.06
     OnTriggerEnter
    0.06
     ř
    0.06
    Act Density 0.008%

    No Known Activations