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

    Neuronpedia

    INDEX
    Explanations

    name

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _In
    -0.07
     laps
    -0.07
     lett
    -0.07
    otion
    -0.07
     bryster
    -0.07
    .post
    -0.07
    unken
    -0.06
    NOT
    -0.06
    .perform
    -0.06
    ན
    -0.06
    POSITIVE LOGITS
     śl
    0.08
    Jvm
    0.07
    窸
    0.07
    方形
    0.07
     Mary
    0.07
     urllib
    0.07
     tables
    0.07
    RequiredMixin
    0.07
    _Al
    0.07
    電子信箱
    0.07
    Act Density 0.014%

    No Known Activations