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

    Neuronpedia

    INDEX
    Explanations

    object spreading and arguments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    anya
    0.71
    lty
    0.68
    intérieur
    0.63
    älte
    0.63
    0.62
    fy
    0.61
    AR
    0.61
    ,
    0.61
    âne
    0.61
    bine
    0.60
    POSITIVE LOGITS
    지
    0.86
    ي
    0.85
    ية
    0.84
    호
    0.82
    са
    0.81
    на
    0.77
    ла
    0.76
    да
    0.76
    ות
    0.72
    у
    0.71
    Act Density 0.050%

    No Known Activations