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

    Neuronpedia

    INDEX
    Explanations

    -H

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ЕН
    -0.07
    vol
    -0.07
    anto
    -0.07
     divergence
    -0.07
    allen
    -0.06
    、何
    -0.06
    -born
    -0.06
    _dist
    -0.06
     For
    -0.06
     offences
    -0.06
    POSITIVE LOGITS
    щина
    0.06
    -х
    0.06
    (image
    0.06
    =========
    0.06
     انسانی
    0.06
    ~-~-~-~-
    0.06
    .cookie
    0.06
     humming
    0.06
     Humans
    0.06
     Naming
    0.06
    Act Density 0.097%

    No Known Activations