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

    Neuronpedia

    INDEX
    Explanations

    excite, excites, excitation, excited

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    س
    0.75
    ీ
    0.73
    ம்
    0.71
    ”。
    0.70
    ります
    0.70
    }).
    0.70
    يين
    0.67
    ור
    0.66
    .'</
    0.66
    ेट
    0.65
    POSITIVE LOGITS
    ↵↵
    1.09
    in
    0.81
    l
    0.80
     from
    0.79
    3
    0.78
    he
    0.77
     FROM
    0.76
    ა
    0.73
    ב
    0.72
    a
    0.71
    Act Density 0.005%

    No Known Activations