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

    Neuronpedia

    INDEX
    Explanations

    command line commands

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    .},
    0.78
    Je
    0.77
    Fer
    0.77
    Respiratory
    0.75
    вина
    0.73
    sembling
    0.72
    okol
    0.68
    Pre
    0.68
    Coe
    0.67
    Street
    0.67
    POSITIVE LOGITS
     --
    1.57
     -
    1.37
     $-
    1.35
     ./
    1.27
     命令
    1.27
     [-
    1.26
     &&
    1.23
     >
    1.19
     <
    1.15
     [--
    1.15
    Act Density 0.358%

    No Known Activations