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

    Neuronpedia

    INDEX
    Explanations

    environment

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Arn
    -0.08
    \Helpers
    -0.07
    _SOC
    -0.07
     ESC
    -0.07
     tablesp
    -0.07
    ệ
    -0.06
     rubbed
    -0.06
     OCR
    -0.06
     würde
    -0.06
    TextField
    -0.06
    POSITIVE LOGITS
    ์ส
    0.06
    ».↵↵
    0.06
    -thinking
    0.06
     impl
    0.06
    Favorite
    0.06
    Од
    0.06
    iration
    0.06
     LU
    0.06
    Neither
    0.06
     torch
    0.06
    Act Density 0.049%

    No Known Activations