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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash

    This neuron fires on Python module‐import keywords (i.e. “import” and “from” statements).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     rm
    -0.07
     Biden
    -0.07
     인기
    -0.07
    Focused
    -0.07
    ;%
    -0.07
     brig
    -0.06
     grapes
    -0.06
     globe
    -0.06
    _args
    -0.06
     gps
    -0.06
    POSITIVE LOGITS
                            ↵
    0.07
    (city
    0.06
     distractions
    0.06
    -refresh
    0.06
    .Project
    0.06
    thritis
    0.06
     तन
    0.06
    .descriptor
    0.06
    軽
    0.06
     接
    0.06
    Act Density 0.149%

    No Known Activations