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
    cv
    -0.07
    obs
    -0.07
    layout
    -0.07
    achine
    -0.06
     lyrics
    -0.06
    Bytes
    -0.06
    FTP
    -0.06
    처럼
    -0.06
    ských
    -0.06
    .comboBox
    -0.06
    POSITIVE LOGITS
    _SELF
    0.07
     stay
    0.07
     attributed
    0.07
     packaged
    0.07
    -labelledby
    0.07
     침
    0.06
    这
    0.06
     produto
    0.06
     χα
    0.06
     settling
    0.06
    Act Density 0.266%

    No Known Activations