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

    Neuronpedia

    INDEX
    Explanations

    computer hardware sizes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Button
    -0.08
    _db
    -0.07
     collectively
    -0.06
    Percent
    -0.06
     buzz
    -0.06
    .CodeAnalysis
    -0.06
     defaultstate
    -0.06
    -project
    -0.06
     cent
    -0.06
     disparities
    -0.06
    POSITIVE LOGITS
     mapStateToProps
    0.06
                            ↵
    0.06
    -yard
    0.06
    .tar
    0.06
     Pee
    0.06
    .optional
    0.06
     ابراه
    0.06
    温度
    0.06
     Dess
    0.06
    ьв
    0.06
    Act Density 0.019%

    No Known Activations