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

    Neuronpedia

    INDEX
    Explanations

    whether or if

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     epitope
    0.44
     Abelian
    0.43
     hyperplane
    0.42
     immunoblot
    0.41
     adjective
    0.40
     oxidative
    0.39
     grueling
    0.39
     dogma
    0.37
     honorable
    0.37
     fickle
    0.37
    POSITIVE LOGITS
    ’
    0.48
    ان
    0.44
    e
    0.40
    ن
    0.40
    quela
    0.39
    گ
    0.38
    ي
    0.38
    ção
    0.37
    ateľ
    0.37
    lı
    0.36
    Act Density 0.344%

    No Known Activations