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

    Neuronpedia

    INDEX
    Explanations

    programmatic instruction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ن
    0.61
    νει
    0.57
    håll
    0.55
     জিনিসের
    0.54
    കൊ
    0.52
    ープ
    0.51
    нов
    0.50
    astica
    0.50
    نیم
    0.50
    тальян
    0.49
    POSITIVE LOGITS
    ;
    0.63
    i
    0.60
    /
    0.60
     as
    0.58
    +
    0.58
    ,
    0.57
    $
    0.55
     -
    0.52
    ',
    0.52
     noisy
    0.52
    Act Density 0.000%

    No Known Activations