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

    Neuronpedia

    INDEX
    Explanations

    :

    np_max-act · gemini-2.0-flash

    The neuron fires on the colon in the “coding:” declaration in file header comments, effectively spotting the encoding‐specifier line in source files.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    GridLayout
    -0.07
    -0.06
    -es
    -0.06
    унк
    -0.06
     vhod
    -0.06
    were
    -0.06
     arcade
    -0.06
     sequences
    -0.06
    conditions
    -0.06
     spontaneous
    -0.06
    POSITIVE LOGITS
    :
    0.08
     :
    0.08
    ्रध
    0.07
    242
    0.07
    ():
    0.07
     gay
    0.07
     elabor
    0.07
    塑
    0.07
     [&
    0.07
     stran
    0.07
    Act Density 0.000%

    No Known Activations