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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    gua
    -1.70
    Gua
    -0.98
     Gua
    -0.95
     gua
    -0.90
    guas
    -0.84
    IsContent
    -0.78
    AccessorTable
    -0.78
    ChromeDriver
    -0.76
    MLLoader
    -0.75
    ContextHolder
    -0.73
    POSITIVE LOGITS
     disso
    0.45
     to
    0.45
    fia
    0.45
     for
    0.43
     Sur
    0.43
     Das
    0.43
    sima
    0.43
    mbia
    0.42
     les
    0.42
     ši
    0.42
    Act Density 0.177%

    No Known Activations