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

    Neuronpedia

    INDEX
    Explanations

    auto, beats, fire, teams

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Prolog
    0.73
     Worcestershire
    0.65
     NumericVector
    0.64
     DIFFIC
    0.63
     RMSE
    0.61
    REA
    0.61
    ప్రత్యర్థి
    0.61
     Hölder
    0.59
     enfe
    0.59
     CentOS
    0.59
    POSITIVE LOGITS
    al
    0.89
    .
    0.77
    ى
    0.75
    و
    0.74
     which
    0.70
     எனப்படும்
    0.70
    es
    0.70
    os
    0.70
    と呼ばれる
    0.66
     como
    0.65
    Act Density 0.004%

    No Known Activations