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

    Neuronpedia

    INDEX
    Explanations

    software code

    np_max-act · gemini-2.0-flash

    This neuron detects programming API or class names (especially CamelCase identifiers) in code snippets.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _MONTH
    -0.07
    _CASE
    -0.07
     essere
    -0.07
     fre
    -0.07
     Québec
    -0.06
     shortcuts
    -0.06
     الجام
    -0.06
     presenta
    -0.06
     sounded
    -0.06
    τεί
    -0.06
    POSITIVE LOGITS
     '!
    0.07
     catch
    0.07
     cue
    0.07
    gambar
    0.06
    具体
    0.06
    idy
    0.06
     serious
    0.06
    ather
    0.06
    .baomidou
    0.06
    =index
    0.06
    Act Density 0.080%

    No Known Activations