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

    Neuronpedia

    INDEX
    Explanations

    breakdown before evaluations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     combinatorial
    0.46
     Lösungen
    0.46
     multiplica
    0.45
     soluções
    0.45
     fondamentali
    0.44
    实施
    0.44
     malattie
    0.44
     líderes
    0.44
     implement
    0.44
     racines
    0.43
    POSITIVE LOGITS
     평가
    0.86
    评价
    0.84
    評価
    0.84
     review
    0.81
     Reviewed
    0.79
    Review
    0.78
     reviewing
    0.78
     reviews
    0.77
     Review
    0.76
     evaluating
    0.75
    Act Density 0.520%

    No Known Activations