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

    Neuronpedia

    INDEX
    Explanations

    organic

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (cell
    -0.06
    еп
    -0.06
    _inds
    -0.06
    ẩm
    -0.06
     liken
    -0.06
     reli
    -0.06
    CEL
    -0.06
    unity
    -0.06
     damages
    -0.06
     У
    -0.06
    POSITIVE LOGITS
    organic
    0.09
    .maven
    0.07
     RPG
    0.07
     Veg
    0.07
     Jar
    0.06
    周年
    0.06
     goggles
    0.06
     scheduling
    0.06
     이동합니다
    0.06
    ostream
    0.06
    Act Density 0.002%

    No Known Activations