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

    Neuronpedia

    INDEX
    Explanations

    CHARSET

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     objeto
    -0.07
     atrav
    -0.07
     Utility
    -0.07
    되지
    -0.07
    (value
    -0.07
     готов
    -0.07
     Superintendent
    -0.06
    initialized
    -0.06
    _NUM
    -0.06
     interven
    -0.06
    POSITIVE LOGITS
    -row
    0.07
    ką
    0.07
     Being
    0.06
    goto
    0.06
    十九大
    0.06
     Benn
    0.06
    _USER
    0.06
     !!!
    0.06
    背后
    0.06
     WIN
    0.06
    Act Density 0.000%

    No Known Activations