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

    Neuronpedia

    INDEX
    Explanations

    great

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Anh
    -0.07
    py
    -0.07
    Delimiter
    -0.07
     torpedo
    -0.06
     Overnight
    -0.06
     scl
    -0.06
    sy
    -0.06
    「你
    -0.06
    िफ
    -0.06
    Sym
    -0.06
    POSITIVE LOGITS
     great
    0.10
     GREAT
    0.07
    _RESULTS
    0.07
     CHO
    0.07
    bbc
    0.06
     کارخانه
    0.06
    broken
    0.06
    いる
    0.06
     cha
    0.06
    дают
    0.06
    Act Density 0.011%

    No Known Activations