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

    Neuronpedia

    INDEX
    Explanations

    number sequences

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    liner
    -0.06
     legs
    -0.06
     obr
    -0.06
    从
    -0.06
    asal
    -0.06
     ull
    -0.06
     une
    -0.06
     достаточно
    -0.06
     Jarvis
    -0.06
     stark
    -0.06
    POSITIVE LOGITS
     battles
    0.07
     Predictor
    0.06
     IService
    0.06
     uncovered
    0.06
    .Evaluate
    0.06
    .`
    0.06
    (dat
    0.06
     Battles
    0.06
    _PAYMENT
    0.06
    (loss
    0.06
    Act Density 0.021%

    No Known Activations