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

    Neuronpedia

    INDEX
    Explanations

    3

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Evaluation
    -0.07
    uitive
    -0.07
     svět
    -0.07
    ativas
    -0.06
     fishing
    -0.06
     Vacuum
    -0.06
    ворю
    -0.06
     negoci
    -0.06
     snippet
    -0.06
    xygen
    -0.06
    POSITIVE LOGITS
    Council
    0.07
    .LOC
    0.06
    _VALID
    0.06
     Counties
    0.06
    必须
    0.06
     hometown
    0.06
    。”
    0.06
     взгляд
    0.06
    startTime
    0.06
    Missing
    0.05
    Act Density 0.000%

    No Known Activations