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

    Neuronpedia

    INDEX
    Explanations

    and

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    د
    0.93
    если
    0.88
    ość
    0.88
     Jeżeli
    0.88
    𝘬
    0.86
    frü
    0.85
    ethylsulfanyl
    0.84
    ości
    0.83
    wq
    0.83
    ди
    0.82
    POSITIVE LOGITS
    '
    1.03
     concisely
    0.97
     and
    0.91
     are
    0.84
     in
    0.82
     accordingly
    0.81
     to
    0.80
    ’
    0.78
     for
    0.74
     across
    0.74
    Act Density 0.550%

    No Known Activations