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

    Neuronpedia

    INDEX
    Explanations

    commands or states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     it
    0.59
    س
    0.57
    స్
    0.57
    ्रेसेस
    0.56
    TE
    0.55
    AL
    0.55
     to
    0.54
    ON
    0.54
    IL
    0.54
    LER
    0.53
    POSITIVE LOGITS
    at
    0.71
    an
    0.62
    ého
    0.59
    and
    0.57
    the
    0.56
    nent
    0.56
    as
    0.56
    asını
    0.54
    andı
    0.54
    ний
    0.54
    Act Density 0.058%

    No Known Activations