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

    Neuronpedia

    INDEX
    Explanations

    js

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ○
    -0.07
    :any
    -0.07
     BOTH
    -0.07
    LOB
    -0.07
    .move
    -0.07
    .directive
    -0.07
    igmoid
    -0.07
    _entry
    -0.07
    BMI
    -0.07
    ğe
    -0.06
    POSITIVE LOGITS
     Eisen
    0.06
     herr
    0.06
     %↵
    0.06
    .getBytes
    0.06
     enjoyment
    0.06
     Кан
    0.06
     tartış
    0.05
    oust
    0.05
     ")
    0.05
    рас
    0.05
    Act Density 0.005%

    No Known Activations