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

    Neuronpedia

    INDEX
    Explanations

    別

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .setAdapter
    -0.07
     mph
    -0.07
    Mark
    -0.07
    ategories
    -0.06
    plot
    -0.06
     doporuč
    -0.06
     getContentPane
    -0.06
    loub
    -0.06
    σου
    -0.06
     Něk
    -0.06
    POSITIVE LOGITS
    (fake
    0.06
    异
    0.06
     experienced
    0.06
    agal
    0.06
    _flash
    0.06
    +',
    0.06
    óż
    0.06
     dst
    0.06
     Tweet
    0.06
    (worker
    0.06
    Act Density 0.005%

    No Known Activations