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

    Neuronpedia

    INDEX
    Explanations

    weighted

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    条件
    -0.07
     cuffs
    -0.06
    達
    -0.06
    男子
    -0.06
     parks
    -0.06
    fixtures
    -0.06
    FromNib
    -0.06
    _mes
    -0.06
    Fu
    -0.05
     Mach
    -0.05
    POSITIVE LOGITS
     weighted
    0.07
     고객
    0.07
     Baths
    0.06
    __;
    0.06
     nebyla
    0.06
     bonus
    0.06
     Лит
    0.06
    bm
    0.06
     watering
    0.06
    Limited
    0.06
    Act Density 0.003%

    No Known Activations