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

    Neuronpedia

    INDEX
    Explanations

    possessive 's following words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ка
    1.08
    و
    1.02
    وو
    0.92
    人员
    0.91
    $-$
    0.89
    𝓀
    0.86
     الهاتف
    0.83
    scriptstyle
    0.83
    स
    0.82
    高度
    0.82
    POSITIVE LOGITS
    ihkan
    1.01
     অতএব
    0.95
    ättning
    0.88
    earch
    0.88
     Own
    0.86
    Novo
    0.85
    ую
    0.85
    ก่
    0.84
     postępow
    0.84
     путь
    0.84
    Act Density 0.154%

    No Known Activations