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

    Neuronpedia

    INDEX
    Explanations

    engineering design, calculations, and support

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    و
    0.80
    IQUE
    0.78
     It
    0.74
    is
    0.72
    I
    0.72
    It
    0.70
    IR
    0.68
    ו
    0.68
    anges
    0.66
    IO
    0.66
    POSITIVE LOGITS
    ۰
    0.82
    ０
    0.68
    .’
    0.66
    ;
    0.66
    )’
    0.64
     in
    0.63
    ),
    0.63
     rebellion
    0.63
     insecurities
    0.63
     inconsistencies
    0.62
    Act Density 0.005%

    No Known Activations