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

    Neuronpedia

    INDEX
    Explanations

    negative interactions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    kwargs
    -0.07
    _metrics
    -0.07
    ugin
    -0.07
     kotlinx
    -0.06
    herited
    -0.06
    GetInstance
    -0.06
     toJson
    -0.06
     Selection
    -0.06
    .filename
    -0.06
    john
    -0.06
    POSITIVE LOGITS
    .DateFormat
    0.07
     عند
    0.07
     цій
    0.06
    ALS
    0.06
    　ﾞ
    0.06
     ACA
    0.06
     Manufacturer
    0.06
     Weak
    0.06
     Cous
    0.06
     Kirst
    0.06
    Act Density 0.013%

    No Known Activations