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

    Neuronpedia

    INDEX
    Explanations

    math equations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     vocation
    -0.08
    ುರ
    -0.08
    Border
    -0.07
     TERR
    -0.07
    border
    -0.07
     adjacent
    -0.07
    Slice
    -0.07
    nade
    -0.07
    -border
    -0.07
    Smile
    -0.07
    POSITIVE LOGITS
     scaling
    0.09
     Scaling
    0.09
     normalization
    0.09
    _kel
    0.08
     Predictions
    0.08
     Giz
    0.08
    Normalization
    0.08
     unchanged
    0.08
     Änderung
    0.08
     plugging
    0.08
    Act Density 0.026%

    No Known Activations