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

    Neuronpedia

    INDEX
    Explanations

    code, notations, lists

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     thanking
    -0.07
    angkan
    -0.06
     än
    -0.06
     пода
    -0.06
    /*!
    -0.06
     повин
    -0.06
     endpoints
    -0.06
    Ω
    -0.06
    ven
    -0.06
    Higher
    -0.06
    POSITIVE LOGITS
    lsruhe
    0.07
    (rel
    0.06
     SNAP
    0.06
    _encoder
    0.06
     Beginner
    0.06
    woff
    0.06
    (Class
    0.06
    /input
    0.06
    -flash
    0.06
    戒
    0.06
    Act Density 0.050%

    No Known Activations