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

    Neuronpedia

    INDEX
    Explanations

    Code and text manipulation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     rebels
    -0.09
     যারা
    -0.08
    (nodes
    -0.08
     nums
    -0.08
     laptops
    -0.07
    (nums
    -0.07
    (vertices
    -0.07
     altru
    -0.07
    uins
    -0.07
     gemstones
    -0.07
    POSITIVE LOGITS
    字符串
    0.16
     문자열
    0.15
    .substring
    0.14
    .Substring
    0.13
    .substr
    0.13
    .split
    0.12
    -string
    0.12
     string
    0.11
     formatted
    0.11
    .gsub
    0.11
    Act Density 0.045%

    No Known Activations