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

    Neuronpedia

    INDEX
    Explanations

    calculate the

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     अध्यक्षता
    0.47
     tehát
    0.45
     Zentral
    0.44
     répét
    0.43
     Denne
    0.43
    nextSend
    0.42
     ਅਤੇ
    0.42
     Werbung
    0.42
     Président
    0.41
     tradizione
    0.41
    POSITIVE LOGITS
     calculate
    0.41
     calculation
    0.39
     easily
    0.38
    ంద
    0.38
     calc
    0.38
    calcul
    0.37
     calcite
    0.37
     persistence
    0.37
     calculates
    0.37
     ens
    0.36
    Act Density 0.001%

    No Known Activations