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

    Neuronpedia

    INDEX
    Explanations

    describe

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Nokia
    -0.06
    laştır
    -0.06
    -gallery
    -0.06
    طه
    -0.06
    示
    -0.06
     underwent
    -0.06
     её
    -0.06
    monthly
    -0.06
    ropolitan
    -0.06
    WINDOWS
    -0.06
    POSITIVE LOGITS
    ет
    0.06
     '/',
    0.06
    [dim
    0.06
     diversos
    0.06
     kills
    0.06
     نیم
    0.06
    aceut
    0.06
    _algo
    0.06
    ็น
    0.06
    Mail
    0.06
    Act Density 0.562%

    No Known Activations