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

    Neuronpedia

    INDEX
    Explanations

    list item numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    து
    1.14
    ܠ
    0.89
    ج
    0.89
    ס
    0.86
    og
    0.85
    소
    0.85
    сть
    0.84
    いた
    0.84
    서
    0.84
    ination
    0.82
    POSITIVE LOGITS
    ریک
    0.99
     spacerItem
    0.93
     Jeho
    0.89
    tey
    0.86
    <0xBA>
    0.86
    رل
    0.86
    ाराम
    0.86
    <0xA3>
    0.85
    वों
    0.84
    ڈنگ
    0.84
    Act Density 0.035%

    No Known Activations