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

    Neuronpedia

    INDEX
    Explanations

    article/possessive

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     auss
    -0.07
     крас
    -0.06
    一个
    -0.06
    =e
    -0.06
    切り
    -0.06
    Ga
    -0.06
    �
    -0.06
    stars
    -0.06
    cheid
    -0.06
     viewModel
    -0.06
    POSITIVE LOGITS
     BRO
    0.07
     mater
    0.06
    Slim
    0.06
    InChildren
    0.06
     DW
    0.06
     çı
    0.06
    /J
    0.06
    (query
    0.06
    },"
    0.06
     Kız
    0.06
    Act Density 0.487%

    No Known Activations