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

    Neuronpedia

    INDEX
    Explanations

    AI assistant questions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _finish
    -0.07
    'u
    -0.06
     cler
    -0.06
     günü
    -0.06
     unveiled
    -0.06
     legalized
    -0.06
    <W
    -0.06
    즌
    -0.05
     PK
    -0.05
    顔
    -0.05
    POSITIVE LOGITS
    (ids
    0.07
    .colorbar
    0.07
     Bars
    0.07
     MenuItem
    0.06
    trap
    0.06
    itr
    0.06
    (prediction
    0.06
    Emer
    0.06
     Sponsored
    0.06
     filings
    0.06
    Act Density 0.028%

    No Known Activations