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

    Neuronpedia

    INDEX
    Explanations

    independently

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    不能为空
    -0.07
    [++
    -0.07
    哭
    -0.07
    .Images
    -0.07
    .border
    -0.07
     içeri
    -0.07
    _appro
    -0.06
    教授
    -0.06
     sû
    -0.06
     doby
    -0.06
    POSITIVE LOGITS
    /*/
    0.07
     cread
    0.06
    (interp
    0.06
    <↵
    0.06
     lobbyists
    0.06
     comentario
    0.06
     프리
    0.06
    953
    0.06
     fu
    0.06
     mutlu
    0.06
    Act Density 0.003%

    No Known Activations