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

    Neuronpedia

    INDEX
    Explanations

    the word "exist"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ية
    1.92
    型的
    1.71
    ри
    1.66
    是谁
    1.59
    所示
    1.53
    การ
    1.52
    ات
    1.51
    )';
    1.47
    ्स
    1.45
    是最
    1.45
    POSITIVE LOGITS
    ש
    2.20
    pipelines
    1.95
    pineapple
    1.83
    ಾಗಲೇ
    1.81
    ن
    1.78
    ﻞ
    1.78
    ﺘ
    1.77
     polít
    1.74
    p
    1.71
    ﾔ
    1.70
    Act Density 0.064%

    No Known Activations