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

    Neuronpedia

    INDEX
    Explanations

    Kiev

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    とはい
    -0.08
     самостоя
    -0.07
    보험
    -0.07
    〘
    -0.07
    放入
    -0.07
     Muse
    -0.07
     giver
    -0.07
    师事务
    -0.07
    周刊
    -0.07
    ⓨ
    -0.07
    POSITIVE LOGITS
    .Parser
    0.07
    .trace
    0.07
    qui
    0.07
    _EXPORT
    0.07
     internal
    0.06
    ﭸ
    0.06
    	api
    0.06
    Wildcard
    0.06
    例外
    0.06
    (expected
    0.06
    Act Density 0.001%

    No Known Activations