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
     testament
    -0.07
     om
    -0.07
     removing
    -0.06
     Testament
    -0.06
     digits
    -0.06
    ackage
    -0.06
    _scalar
    -0.06
     persons
    -0.06
    <Account
    -0.06
     Merc
    -0.06
    POSITIVE LOGITS
     predictions
    0.08
    (prediction
    0.07
    -finals
    0.07
    krát
    0.07
    _preds
    0.07
     alcan
    0.06
    ista
    0.06
     Üç
    0.06
    즘
    0.06
    λικά
    0.06
    Act Density 0.009%

    No Known Activations