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

    Neuronpedia

    INDEX
    Explanations

    Code, URLs, file paths

    np_max-act-logits · gemini-2.0-flashTriggered by @bettyfeng2003
    New Auto-Interp
    Negative Logits
    +-+-
    -0.08
    陞
    -0.08
    怅
    -0.08
    */)
    -0.07
     versa
    -0.07
    涝
    -0.07
    💮
    -0.07
    ➧
    -0.07
    ڀ
    -0.07
    😺
    -0.07
    POSITIVE LOGITS
    eceği
    0.07
     يكون
    0.07
    Mini
    0.07
     groundwork
    0.07
    Name
    0.07
    DisplayName
    0.07
    _GO
    0.06
    Fo
    0.06
    id
    0.06
    دو
    0.06
    Act Density 1.417%

    No Known Activations