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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     deb
    -0.06
     inhibition
    -0.06
     Admission
    -0.06
     almış
    -0.06
    是个
    -0.06
     Anton
    -0.06
    Gap
    -0.06
    benchmark
    -0.05
     Carm
    -0.05
    _tmp
    -0.05
    POSITIVE LOGITS
    šť
    0.07
    σιμοποι
    0.07
    _grupo
    0.07
    .effects
    0.07
    尘
    0.06
     khu
    0.06
    -selector
    0.06
    /**/*.
    0.06
    oundary
    0.06
     نسمة
    0.06
    Act Density 0.002%

    No Known Activations