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

    Neuronpedia

    INDEX
    Explanations

    Code, files, programming

    np_max-act · gemini-2.0-flash

    The neuron is strongly activated by programming‐language identifier tokens (e.g. class, module, or file names).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    -0.06
     temperament
    -0.06
    .NewReader
    -0.06
    :UIControlEvent
    -0.06
    Converted
    -0.06
     lấy
    -0.06
    &a
    -0.06
     noon
    -0.05
    -0.05
     تحلیل
    -0.05
    POSITIVE LOGITS
     horrible
    0.07
     xlink
    0.07
     股
    0.06
    liga
    0.06
     biological
    0.06
    :@"%
    0.06
    .inc
    0.06
    \C
    0.06
    -orange
    0.06
    mnt
    0.06
    Act Density 0.049%

    No Known Activations