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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    awl
    -0.08
    äm
    -0.07
     Rabbit
    -0.06
    _GROUP
    -0.06
     send
    -0.06
     Toby
    -0.06
    wid
    -0.06
     AIDS
    -0.06
    .isDebugEnabled
    -0.06
    Tip
    -0.06
    POSITIVE LOGITS
    етель
    0.07
    .aspx
    0.07
     MainMenu
    0.07
     yiy
    0.07
    .features
    0.06
     advoc
    0.06
    赞
    0.06
    下来
    0.06
    _tickets
    0.06
    (named
    0.06
    Act Density 0.133%

    No Known Activations