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

    Neuronpedia

    INDEX
    Explanations

    THE VOICE, TRUE if

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     that
    1.28
    that
    1.28
     IFN
    1.18
    人が
    1.13
     वह
    1.09
    ş
    1.06
    you
    1.05
    și
    1.05
     UX
    1.04
     उत्पा
    1.03
    POSITIVE LOGITS
    ↵
    1.77
    ہ
    1.66
    the
    1.60
    اس
    1.50
    to
    1.47
    на
    1.45
    ER
    1.45
     are
    1.42
    :
    1.41
    The
    1.41
    Act Density 0.594%

    No Known Activations