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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash

    This neuron activates on code identifiers (variable names, function names, and other non-natural-language tokens) in programming snippets.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ैच
    -0.06
    _markers
    -0.06
    Candidates
    -0.06
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    -0.06
    :"-"`↵
    -0.05
    volution
    -0.05
    /the
    -0.05
    Factory
    -0.05
    _itr
    -0.05
    FindObject
    -0.05
    POSITIVE LOGITS
    decode
    0.06
     volleyball
    0.06
     welfare
    0.06
    偏
    0.06
     Drops
    0.06
    .za
    0.06
    _COLL
    0.06
     mL
    0.06
    Edges
    0.06
    click
    0.06
    Act Density 0.539%

    No Known Activations