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

    Neuronpedia

    INDEX
    Explanations

    sameness or equivalence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ap
    0.44
     foreseen
    0.42
     ap
    0.41
    iap
    0.39
     απο
    0.39
    AP
    0.38
    apache
    0.38
     }}(
    0.38
     апо
    0.38
     एपी
    0.38
    POSITIVE LOGITS
     same
    0.74
    Same
    0.68
     Same
    0.63
    same
    0.62
    同じ
    0.62
     stessa
    0.60
     misma
    0.59
     hetzelfde
    0.57
     mismo
    0.56
     samma
    0.56
    Act Density 0.003%

    No Known Activations