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

    Neuronpedia

    INDEX
    Explanations

    Code and chemical formulas

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    جعل
    -0.07
    =username
    -0.07
    就成了
    -0.07
    PostMapping
    -0.07
    .action
    -0.07
    PRICE
    -0.07
    更是
    -0.07
    =email
    -0.06
    finite
    -0.06
    (reverse
    -0.06
    POSITIVE LOGITS
    ル
    0.07
    鸽
    0.07
    ヮ
    0.07
    �
    0.07
    ER
    0.07
     нарко
    0.06
     الدني
    0.06
    知识分子
    0.06
     gettimeofday
    0.06
    🏗
    0.06
    Act Density 0.203%

    No Known Activations