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

    Neuronpedia

    INDEX
    Explanations

    binary

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    DidEnter
    -0.07
     submerged
    -0.07
    ूं
    -0.06
    SEQU
    -0.06
    enson
    -0.06
    >About
    -0.06
    條
    -0.06
    Div
    -0.06
     формы
    -0.06
     الشخص
    -0.06
    POSITIVE LOGITS
    predict
    0.07
    _zeros
    0.07
    Updates
    0.06
    -products
    0.06
     ؟
    0.06
    structures
    0.06
    ś
    0.06
    actoring
    0.06
    wind
    0.06
    ############################################################################
    0.06
    Act Density 0.000%

    No Known Activations