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

    Neuronpedia

    INDEX
    Explanations

    unknown variables

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     teny
    -0.08
     panc
    -0.08
    -М
    -0.08
    udp
    -0.08
     LL
    -0.08
     فرهنگ
    -0.07
     sumptuous
    -0.07
     MIME
    -0.07
    tees
    -0.07
     curated
    -0.07
    POSITIVE LOGITS
    变量
    0.13
    .variables
    0.12
     variables
    0.12
     변수
    0.12
    Variables
    0.12
     Variables
    0.12
    _variables
    0.11
    _VARIABLE
    0.11
     algebra
    0.10
    .variable
    0.10
    Act Density 0.028%

    No Known Activations