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

    Neuronpedia

    INDEX
    Explanations

    magnetic spin properties

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     மாசு
    0.44
     فهر
    0.41
     photoelectric
    0.41
     searchValue
    0.40
    bedo
    0.39
     برق
    0.39
    PHOTO
    0.39
     PHOTO
    0.38
     kapcsolat
    0.38
     dazz
    0.38
    POSITIVE LOGITS
     domain
    0.56
     reversal
    0.55
     Né
    0.55
     sky
    0.54
     Domain
    0.53
    Domain
    0.52
    domain
    0.49
     spins
    0.49
    Exchange
    0.48
     exchange
    0.47
    Act Density 0.009%

    No Known Activations