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

    Neuronpedia

    INDEX
    Explanations

    construction projects

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    得罪
    -0.07
    psilon
    -0.07
    מטר
    -0.07
    evt
    -0.07
    佛
    -0.06
    find
    -0.06
    姓
    -0.06
    征集
    -0.06
     crave
    -0.06
    .GetCurrentMethod
    -0.06
    POSITIVE LOGITS
    acles
    0.07
    alink
    0.07
    /pm
    0.07
     Tate
    0.07
    setLabel
    0.06
    RegularExpression
    0.06
    콸
    0.06
    upyter
    0.06
     Liverpool
    0.06
     Tome
    0.06
    Act Density 0.049%

    No Known Activations