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

    Neuronpedia

    INDEX
    Explanations

    business and tech abbreviations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    l
    1.32
    datei
    1.22
    tidak
    1.21
    lah
    1.12
    on
    1.11
    cional
    1.11
    শ্বরের
    1.11
    lere
    1.08
    ième
    1.08
    ez
    1.06
    POSITIVE LOGITS
    এ
    1.03
    ّ
    0.98
    に
    0.96
    м
    0.94
    ឍ
    0.92
    в
    0.92
    에
    0.91
    ها
    0.87
    вят
    0.87
     алыңыз
    0.85
    Act Density 0.593%

    No Known Activations