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

    Neuronpedia

    INDEX
    Explanations

    world position

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ل
    1.02
    lendi
    0.96
    ब
    0.93
    습니다
    0.89
    ל
    0.88
    чі
    0.87
    是不
    0.87
    મ
    0.85
    ما
    0.85
    BUT
    0.85
    POSITIVE LOGITS
     judicious
    0.88
     periód
    0.85
     Xeon
    0.79
     XOR
    0.79
     appet
    0.78
     jov
    0.78
     modulus
    0.78
     técn
    0.77
     ROI
    0.77
     JFrame
    0.77
    Act Density 0.000%

    No Known Activations