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

    Neuronpedia

    INDEX
    Explanations

    rebel and rebellion against

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ра
    1.22
    of
    0.98
    ي
    0.98
    ी
    0.97
    не
    0.95
    и
    0.91
    ла
    0.91
    ला
    0.88
    p
    0.87
    و
    0.84
    POSITIVE LOGITS
     rebell
    0.92
     rebels
    0.87
     rebel
    0.86
     Rebellion
    0.81
     বিদ্রোহ
    0.77
     revolt
    0.76
     विद्रोह
    0.73
     rebellion
    0.71
     Rebels
    0.71
     Rebel
    0.68
    Act Density 0.007%

    No Known Activations