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

    Neuronpedia

    INDEX
    Explanations

    power and related compound phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    اريخ
    0.42
    }=(\
    0.40
    糇
    0.40
    spark
    0.39
    rych
    0.39
    血压
    0.38
     Bibliothek
    0.38
    ભ્ય
    0.38
    ník
    0.37
    yat
    0.37
    POSITIVE LOGITS
     power
    0.84
    Power
    0.76
     Power
    0.76
    power
    0.70
    lessness
    0.70
     powert
    0.66
     puterea
    0.64
     पावर
    0.60
     adquis
    0.60
     POWER
    0.59
    Act Density 0.039%

    No Known Activations