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

    Neuronpedia

    INDEX
    Explanations

    Time frames (early, later)

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     banco
    -0.07
     forgiveness
    -0.07
    agua
    -0.06
    steel
    -0.06
    ryan
    -0.06
    faith
    -0.06
    .der
    -0.06
    [class
    -0.06
    نگ
    -0.06
     tá
    -0.06
    POSITIVE LOGITS
     ainsi
    0.07
     phổ
    0.06
    _UNIFORM
    0.06
    ozo
    0.06
     estados
    0.06
    directory
    0.06
    [A
    0.06
    -operative
    0.06
     Pix
    0.06
     EXPER
    0.06
    Act Density 0.023%

    No Known Activations