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

    Neuronpedia

    INDEX
    Explanations

    recursive

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     status
    -0.07
     мав
    -0.07
    block
    -0.06
     intoler
    -0.06
     свят
    -0.06
     Bed
    -0.06
    .tokenize
    -0.06
    ル
    -0.06
    BAT
    -0.06
     disple
    -0.06
    POSITIVE LOGITS
     recursive
    0.16
    Recursive
    0.14
     Recursive
    0.13
    recursive
    0.12
     recursively
    0.11
     recursion
    0.09
     recurse
    0.09
    ursion
    0.08
    归
    0.08
    recur
    0.08
    Act Density 0.003%

    No Known Activations