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

    Neuronpedia

    INDEX
    Explanations

    must to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     opak
    -0.07
    _bw
    -0.06
     nổi
    -0.06
    .communication
    -0.06
     centroids
    -0.06
     dazu
    -0.06
     tostring
    -0.06
    _adc
    -0.06
     knots
    -0.06
    (Parse
    -0.06
    POSITIVE LOGITS
    ্�
    0.07
     integrated
    0.06
    sss
    0.06
    )<
    0.06
    .isEnabled
    0.06
     Lamb
    0.06
     Craft
    0.06
     selection
    0.06
    -ex
    0.06
     responsibility
    0.06
    Act Density 0.058%

    No Known Activations