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

    Neuronpedia

    INDEX
    Explanations

    PDF reader

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    est
    0.61
    е
    0.58
    esto
    0.57
    ó
    0.57
    ended
    0.56
    спа
    0.56
    ar
    0.55
    asters
    0.53
    ce
    0.53
    ia
    0.53
    POSITIVE LOGITS
     Haryana
    0.67
     ऑफिस
    0.59
     Uttar
    0.59
     Uttarakhand
    0.57
     TouchUtils
    0.57
     Fuerza
    0.55
     bhavati
    0.55
    राइड
    0.55
     Pawan
    0.55
     ഉണ്ടാ
    0.54
    Act Density 0.001%

    No Known Activations