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

    Neuronpedia

    INDEX
    Explanations

    Suffixes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    205
    -0.07
    154
    -0.07
    Ind
    -0.07
     getRandom
    -0.06
    (num
    -0.06
     mb
    -0.06
    124
    -0.06
     fs
    -0.06
    �ng
    -0.06
     kwargs
    -0.06
    POSITIVE LOGITS
    _router
    0.07
     souvent
    0.06
     oppressed
    0.06
     шаг
    0.06
    0.06
     форм
    0.06
     μό
    0.06
     trabalho
    0.06
     такого
    0.06
    fieldname
    0.06
    Act Density 0.179%

    No Known Activations