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

    Neuronpedia

    INDEX
    Explanations

    appears in or on

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ي
    0.94
    י
    0.84
    ก็
    0.81
    あ
    0.81
    بي
    0.81
    ه
    0.75
    ブ
    0.75
     it
    0.73
    מ
    0.73
    س
    0.72
    POSITIVE LOGITS
    in
    0.88
     appears
    0.84
     appear
    0.82
    im
    0.80
    is
    0.73
     Appear
    0.71
    রা
    0.71
    at
    0.68
    appears
    0.68
    il
    0.66
    Act Density 0.018%

    No Known Activations