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

    Neuronpedia

    INDEX
    Explanations

    .

    np_max-act · gemini-2.0-flash

    This neuron detects occurrences of the “..” marker that introduce reStructuredText directives or comments.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    白
    -0.08
     millis
    -0.07
    式
    -0.07
    ello
    -0.07
    Japgolly
    -0.06
     прест
    -0.06
    Profile
    -0.06
    _j
    -0.06
     strat
    -0.06
     badge
    -0.06
    POSITIVE LOGITS
    ..
    0.09
    ीतर
    0.07
    ..
    0.07
    ोषण
    0.07
    椅
    0.06
     institution
    0.06
    CED
    0.06
     Mariners
    0.06
     luxurious
    0.06
    (exports
    0.06
    Act Density 0.000%

    No Known Activations