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

    Neuronpedia

    INDEX
    Explanations

    statistical models and regressions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     credentials
    -0.08
    ょう
    -0.08
     rato
    -0.08
    cipher
    -0.08
     �
    -0.08
     estup
    -0.08
    (bt
    -0.08
    ává
    -0.08
     wick
    -0.08
    credentials
    -0.08
    POSITIVE LOGITS
     biases
    0.11
     bias
    0.11
    Bias
    0.10
     Bias
    0.10
    .bias
    0.09
    bias
    0.09
    _bias
    0.08
     biais
    0.08
     fluctuations
    0.08
     ramach
    0.08
    Act Density 0.001%

    No Known Activations