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

    Neuronpedia

    INDEX
    Explanations

    Spanish actions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Value
    -0.07
    when
    -0.07
    oltage
    -0.07
     Lage
    -0.07
    please
    -0.07
    pdo
    -0.07
    nde
    -0.07
    lose
    -0.07
     onları
    -0.07
    ksi
    -0.06
    POSITIVE LOGITS
    *R
    0.06
    BitFields
    0.06
     Sür
    0.06
     Prosec
    0.06
     utiliser
    0.06
     Fortunately
    0.06
    犯
    0.06
     UR
    0.06
    SR
    0.06
     dictator
    0.06
    Act Density 0.119%

    No Known Activations