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

    Neuronpedia

    INDEX
    Explanations

    author

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     각
    -0.07
     adorned
    -0.06
     pulumi
    -0.06
     status
    -0.06
     channels
    -0.06
     ZEND
    -0.06
     Scatter
    -0.06
    混合
    -0.06
     محل
    -0.06
     hubs
    -0.06
    POSITIVE LOGITS
    by
    0.11
     by
    0.08
    By
    0.07
    abh
    0.07
    ność
    0.06
    602
    0.06
    _by
    0.06
     implicitly
    0.06
     isp
    0.06
    ammer
    0.06
    Act Density 0.003%

    No Known Activations