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

    Neuronpedia

    INDEX
    Explanations

    mathematical formulas

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.09
    担当
    -0.09
     вод
    -0.09
    stil
    -0.08
    -0.08
     insists
    -0.08
    _PICK
    -0.08
     �
    -0.08
     واضحة
    -0.08
    UTERS
    -0.07
    POSITIVE LOGITS
     scaling
    0.09
    _final
    0.09
    Scaling
    0.09
    }/
    0.08
    _n
    0.08
    _scaled
    0.08
     GF
    0.08
    _scal
    0.08
    formula
    0.08
     Scaling
    0.08
    Act Density 0.030%
    No Known Activations