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

    Neuronpedia

    INDEX
    Explanations

    cebolla

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    फना
    0.43
    َق
    0.42
    ði
    0.41
    ~.,
    0.41
     नाही
    0.39
     Thi
    0.39
     BWR
    0.39
     ধৈ
    0.38
     Ferrari
    0.38
     Rodrigo
    0.38
    POSITIVE LOGITS
    נית
    0.85
    ניות
    0.75
    לית
    0.71
    nit
    0.58
    нит
    0.57
    נן
    0.51
    Ta
    0.46
    نية
    0.45
    נון
    0.45
    יות
    0.44
    Act Density 0.000%

    No Known Activations