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

    Neuronpedia

    INDEX
    Explanations

    legal citations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Azure
    -0.07
     Antar
    -0.06
    ied
    -0.06
    "),
    -0.06
     Snackbar
    -0.06
     खर
    -0.06
     даже
    -0.06
     juin
    -0.06
     martyr
    -0.06
     Human
    -0.06
    POSITIVE LOGITS
     será
    0.07
     tilt
    0.06
     Units
    0.06
    (Logger
    0.06
     bruises
    0.06
    _locked
    0.06
    :f
    0.06
     deduct
    0.06
     Gi�
    0.06
    .strictEqual
    0.06
    Act Density 0.002%

    No Known Activations