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

    Neuronpedia

    INDEX
    Explanations

    predictions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sensed
    -0.08
     필
    -0.07
     felt
    -0.06
     tùy
    -0.06
     Поль
    -0.06
     RNA
    -0.06
    .Ptr
    -0.06
     cít
    -0.06
     Св
    -0.06
    _tF
    -0.06
    POSITIVE LOGITS
     predictions
    0.27
    predictions
    0.11
     prediction
    0.10
     preds
    0.08
    prediction
    0.08
    _preds
    0.07
    .transaction
    0.07
    entries
    0.07
    818
    0.07
    ध
    0.06
    Act Density 0.006%

    No Known Activations