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

    Neuronpedia

    INDEX
    Explanations

    Quantity words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cuenta
    -0.08
     потер
    -0.07
     Rout
    -0.07
    فعل
    -0.07
    鸳
    -0.06
    财力
    -0.06
    媸
    -0.06
     Washington
    -0.06
     Algorithms
    -0.06
    }[
    -0.06
    POSITIVE LOGITS
    לידה
    0.07
    obile
    0.07
    abis
    0.07
    FIELDS
    0.07
    ちなみ
    0.06
    褯
    0.06
    Div
    0.06
    缭
    0.06
    memory
    0.06
     ActiveForm
    0.06
    Act Density 0.285%

    No Known Activations