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

    Neuronpedia

    INDEX
    Explanations

    constructed within, equations with fractions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Erb
    0.45
     acc
    0.41
     Pow
    0.41
     poi
    0.41
     pow
    0.41
     Dell
    0.39
    acide
    0.39
     Poi
    0.38
     Acc
    0.38
     Schweizer
    0.38
    POSITIVE LOGITS
     entrev
    0.45
    しよう
    0.44
    lcnaf
    0.42
    neys
    0.42
    ㄈ
    0.40
    норийска
    0.39
    getBlueTeam
    0.39
    <unused52>
    0.39
    ído
    0.39
    λεύ
    0.39
    Act Density 0.000%

    No Known Activations