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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash

    The neuron responds to tokens made up entirely of spaces (i.e. indentation or blank‐line whitespace).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    Python programming techniques and functionalities related to file and directory manipulation.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     الآ
    -0.06
    хи
    -0.06
    Images
    -0.06
    Estado
    -0.06
     Mes
    -0.06
     interesse
    -0.05
    ुण
    -0.05
    ocrine
    -0.05
     История
    -0.05
    sian
    -0.05
    POSITIVE LOGITS
    .Other
    0.07
     एव
    0.06
    tk
    0.06
     _("
    0.06
    _plot
    0.06
     sadly
    0.06
    .${
    0.06
     endorsed
    0.06
          ↵
    0.06
     refreshToken
    0.06
    Act Density 0.044%

    No Known Activations