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

    Neuronpedia

    INDEX
    Explanations

    communication

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    寿命
    -0.08
    (init
    -0.07
    structuring
    -0.07
    angement
    -0.07
    삶
    -0.07
    интер
    -0.07
     sư
    -0.06
     Assertions
    -0.06
     Manufacturing
    -0.06
    _String
    -0.06
    POSITIVE LOGITS
    xfd
    0.07
    评论
    0.07
     sky
    0.07
    _if
    0.06
    _BASE
    0.06
     حياته
    0.06
    #'
    0.06
    Thai
    0.06
    -connect
    0.06
    ䷸
    0.06
    Act Density 0.168%

    No Known Activations