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

    Neuronpedia

    INDEX
    Explanations

    eight concepts and numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    A
    0.70
    zerű
    0.64
    ح
    0.60
    jų
    0.58
     TA
    0.58
     پا
    0.58
    ko
    0.57
    zx
    0.57
    á
    0.56
    ão
    0.56
    POSITIVE LOGITS
    যখন
    0.55
     capitalismo
    0.53
     citizenry
    0.53
     cran
    0.52
     vina
    0.52
     humanist
    0.52
    wellness
    0.52
     lorsque
    0.50
     organics
    0.50
     alkalies
    0.50
    Act Density 0.025%

    No Known Activations