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

    Neuronpedia

    INDEX
    Explanations

    feels none

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Gaur
    0.76
    iénd
    0.74
    fontWeight
    0.72
     źród
    0.72
     emerging
    0.69
    Olá
    0.68
     fuentes
    0.68
     worried
    0.68
    Sources
    0.68
     concerned
    0.67
    POSITIVE LOGITS
     No
    1.06
     no
    0.97
    No
    0.90
    no
    0.81
    ที่เรา
    0.72
     MATLAB
    0.68
     NO
    0.68
     trait
    0.66
    我们将
    0.66
     NUM
    0.65
    Act Density 0.000%

    No Known Activations