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

    Neuronpedia

    INDEX
    Explanations

    equals sign

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Санкт
    -0.08
    .ravel
    -0.07
     NY
    -0.07
     gently
    -0.07
    分明
    -0.07
    ,*
    -0.07
    苑
    -0.07
    へ
    -0.07
    ƞ
    -0.07
    �
    -0.07
    POSITIVE LOGITS
    _Description
    0.06
    (room
    0.06
     gear
    0.06
    也没什么
    0.06
    curso
    0.06
    يح
    0.06
    .Blocks
    0.06
     Galactic
    0.06
    "Why
    0.06
    推薦
    0.06
    Act Density 0.003%

    No Known Activations