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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -0.07
    erve
    -0.06
    scss
    -0.06
    Encode
    -0.06
     Pel
    -0.06
    alysis
    -0.06
    .autoconfigure
    -0.06
     Dude
    -0.06
    icamente
    -0.06
     penetration
    -0.06
    POSITIVE LOGITS
     seeking
    0.08
    _mt
    0.07
    ırken
    0.07
    .registry
    0.07
    :self
    0.06
    获得
    0.06
     отмет
    0.06
     없었다
    0.06
     mimo
    0.06
     onNext
    0.06
    Act Density 0.001%
    No Known Activations