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

    Neuronpedia

    INDEX
    Explanations

    specific identifiers often followed by delimiters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     (
    0.81
     ہوگا۔
    0.80
    ငံ
    0.79
     होगा
    0.77
    on
    0.76
     आएगा
    0.73
     όλα
    0.73
    䍜
    0.71
     уди
    0.70
    িব
    0.69
    POSITIVE LOGITS
    :
    1.30
    ;
    1.25
    #
    0.93
    %
    0.91
    3
    0.87
    "
    0.85
    ৩
    0.85
    ?
    0.81
    9
    0.79
    <0x91>
    0.78
    Act Density 0.000%

    No Known Activations