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

    Neuronpedia

    INDEX
    Explanations

    Descriptive text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    VERT
    -0.06
    허
    -0.06
    」を
    -0.06
     Tor
    -0.06
    Constant
    -0.06
    (dialog
    -0.06
    .getContext
    -0.06
     Enh
    -0.06
    =L
    -0.06
    ิตย
    -0.06
    POSITIVE LOGITS
    ským
    0.07
    _GOOD
    0.07
    .npy
    0.06
    tog
    0.06
     evils
    0.06
    χος
    0.06
    ों,
    0.06
     Sole
    0.06
     Slider
    0.06
    کز
    0.06
    Act Density 0.250%

    No Known Activations