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

    Neuronpedia

    INDEX
    Explanations

    0 or 5

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ଓ
    -0.08
     rocker
    -0.07
    _cn
    -0.07
    伾
    -0.07
     lobbyists
    -0.07
    outlined
    -0.07
     comedian
    -0.07
     roommate
    -0.07
    玱
    -0.06
     nhé
    -0.06
    POSITIVE LOGITS
    buzz
    0.07
     등을
    0.07
    湿润
    0.07
    不了解
    0.07
     Pierre
    0.06
    不懂
    0.06
    ')])↵
    0.06
    _second
    0.06
    找了
    0.06
    tim
    0.06
    Act Density 0.029%

    No Known Activations