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

    Neuronpedia

    INDEX
    Explanations

    form

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    摇滚
    -0.08
    ⎈
    -0.08
    琢
    -0.07
     ModelRenderer
    -0.07
    宏伟
    -0.07
     KD
    -0.07
    .list
    -0.07
    欣喜
    -0.06
    活跃
    -0.06
    endant
    -0.06
    POSITIVE LOGITS
    更何况
    0.08
     implicated
    0.07
    ITIONAL
    0.07
    _emails
    0.07
     aunque
    0.07
    といった
    0.07
    	game
    0.07
     tyre
    0.07
    ([]);↵
    0.07
    脸部
    0.07
    Act Density 0.001%

    No Known Activations