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

    Neuronpedia

    INDEX
    Explanations

    list section divider

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    жений
    0.71
     multiples
    0.71
    тента
    0.67
    quadratic
    0.66
    во
    0.65
    ית
    0.65
    дя
    0.64
    ियन
    0.63
    মন্ত্রী
    0.63
     dequeue
    0.63
    POSITIVE LOGITS
     Dura
    0.85
     Hệ
    0.84
     Mudah
    0.82
     Daftar
    0.82
     Cơ
    0.80
     ofrece
    0.80
    ্থ
    0.79
     ambayo
    0.79
    ಫ್
    0.78
     bentuk
    0.76
    Act Density 0.001%

    No Known Activations