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

    Neuronpedia

    INDEX
    Explanations

    Rephrasing/clarifying

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    iedade
    -0.07
    /content
    -0.07
    ﯘ
    -0.07
     psyche
    -0.07
    实实在在
    -0.06
    缉
    -0.06
    西安
    -0.06
    IEEE
    -0.06
    aleza
    -0.06
    ꦨ
    -0.06
    POSITIVE LOGITS
    彈
    0.07
    ILE
    0.07
    [String
    0.07
    unds
    0.07
    refresh
    0.07
    �
    0.06
    .Last
    0.06
    生产基地
    0.06
     Player
    0.06
    ,)↵
    0.06
    Act Density 0.076%

    No Known Activations