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

    Neuronpedia

    INDEX
    Explanations

    s

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Hide
    -0.07
    (MSG
    -0.07
    hint
    -0.07
     ç
    -0.07
    ────
    -0.07
    adjusted
    -0.07
     صرف
    -0.06
     Sở
    -0.06
    prop
    -0.06
    azaar
    -0.06
    POSITIVE LOGITS
     بانک
    0.06
     toán
    0.06
    _poll
    0.06
    Blake
    0.06
     robotics
    0.06
    -produ
    0.06
    Denver
    0.06
    .poll
    0.06
    Bush
    0.06
     heated
    0.06
    Act Density 0.000%

    No Known Activations