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

    Neuronpedia

    INDEX
    Explanations

    surveys

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Semaphore
    -0.08
     plaf
    -0.08
     boundaries
    -0.08
    Combination
    -0.08
     grenzen
    -0.08
     시설
    -0.08
    Expr
    -0.08
     склон
    -0.07
     tect
    -0.07
     plafond
    -0.07
    POSITIVE LOGITS
     قصيرة
    0.11
     קצר
    0.10
     സമയം
    0.10
    時間
    0.10
     aega
    0.10
     aikaa
    0.10
     dauert
    0.09
     dauern
    0.09
     وقت
    0.09
     pochi
    0.09
    Act Density 0.026%

    No Known Activations