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

    Neuronpedia

    INDEX
    Explanations

    miracle

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    辕
    2.52
     Synth
    1.89
    い
    1.83
    轅
    1.76
     thiểu
    1.74
     Auth
    1.68
    或许
    1.68
     Sections
    1.64
     Obj
    1.63
     Thes
    1.63
    POSITIVE LOGITS
    و
    2.38
    ли
    2.13
    Я
    2.09
    atte
    2.02
    И
    1.98
    기
    1.97
    ي
    1.89
    ку
    1.84
     использования
    1.82
    ată
    1.80
    Act Density 0.002%

    No Known Activations