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

    Neuronpedia

    INDEX
    Explanations

    code and data structures

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    odem
    -0.07
    	cal
    -0.07
    豆浆
    -0.07
     Rat
    -0.07
    ;y
    -0.07
    衲
    -0.07
    �
    -0.07
    coc
    -0.06
     Corn
    -0.06
     McK
    -0.06
    POSITIVE LOGITS
    后台
    0.07
     administered
    0.07
    nginx
    0.07
    _winner
    0.07
    HttpException
    0.07
    PLAYER
    0.07
    (serializer
    0.07
    는데
    0.07
    ⇨
    0.07
    十六条
    0.07
    Act Density 0.000%

    No Known Activations