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

    Neuronpedia

    INDEX
    Explanations

    installing python packages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     utilidad
    1.03
     heralded
    0.97
    ERCIAL
    0.97
    пону
    0.96
     целей
    0.95
    ambilan
    0.95
    Antaeotricha
    0.95
     המח
    0.95
    DrvGPIO
    0.90
     gén
    0.88
    POSITIVE LOGITS
    [,
    0.75
    percentage
    0.75
    ون
    0.70
    ||
    0.69
    [[
    0.69
    [$
    0.69
     eq
    0.67
    primary
    0.67
     &&
    0.66
    &&
    0.66
    Act Density 0.024%

    No Known Activations