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

    Neuronpedia

    INDEX
    Explanations

    opening doors to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    abilität
    0.69
    ي
    0.67
    ach
    0.66
    कर्ता
    0.63
    вати
    0.61
    ul
    0.61
    the
    0.59
    cies
    0.59
    ಂಬ
    0.59
    is
    0.58
    POSITIVE LOGITS
     $
    0.71
     \\
    0.66
     \
    0.65
    0.61
    </i>
    0.61
    你
    0.60
     '
    0.60
    ாலை
    0.59
    া
    0.59
    8
    0.59
    Act Density 0.002%

    No Known Activations