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

    Neuronpedia

    INDEX
    Explanations

    negative descriptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mortality
    -0.06
    yll
    -0.06
    词
    -0.06
     lane
    -0.06
     pró
    -0.06
     observer
    -0.06
     vara
    -0.06
    ﾞ
    -0.06
    合格
    -0.06
    gesture
    -0.06
    POSITIVE LOGITS
    =date
    0.07
    glich
    0.07
    сии
    0.06
     CSC
    0.06
    ErrorException
    0.06
     APK
    0.06
    _FLAGS
    0.06
     Gluten
    0.06
     Float
    0.06
    ãeste
    0.06
    Act Density 0.052%

    No Known Activations