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

    Neuronpedia

    INDEX
    Explanations

    lecturer

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    相对于
    -0.08
    	pstmt
    -0.07
    (chain
    -0.07
    ȋ
    -0.07
    sure
    -0.07
    隨時
    -0.07
    _SCHEDULE
    -0.07
    sword
    -0.07
     nghìn
    -0.07
    ǭ
    -0.06
    POSITIVE LOGITS
     ברח
    0.07
    תאריך
    0.07
     Arabic
    0.07
     hoax
    0.07
     #[
    0.07
    .library
    0.07
     typingsJapgolly
    0.07
    #[
    0.07
     dotyczące
    0.07
     //
↵
    0.06
    Act Density 0.002%

    No Known Activations