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

    Neuronpedia

    INDEX
    Explanations

    measurements over time

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _SIDE
    -0.07
     alphabet
    -0.07
    odyn
    -0.06
     verbs
    -0.06
     ders
    -0.06
     synchronized
    -0.06
     necessário
    -0.06
    _NONNULL
    -0.06
    output
    -0.06
     Observable
    -0.06
    POSITIVE LOGITS
     Sim
    0.07
    Est
    0.07
    監督
    0.06
    алов
    0.06
    (off
    0.06
     темп
    0.06
    atisfied
    0.06
     Ком
    0.06
    /cat
    0.06
     ас
    0.06
    Act Density 0.016%

    No Known Activations