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

    Neuronpedia

    INDEX
    Explanations

    install

    np_max-act · gemini-2.0-flash

    This neuron detects package installation commands (e.g., “pip install …”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     missile
    -0.07
     THC
    -0.06
     methodology
    -0.06
    .Rule
    -0.06
    _weapon
    -0.06
     pool
    -0.06
     metaData
    -0.06
     egg
    -0.06
     комплекс
    -0.06
     chaos
    -0.06
    POSITIVE LOGITS
     edible
    0.07
    Stand
    0.07
     splitting
    0.06
     Dmitry
    0.06
     Ung
    0.06
     Dough
    0.06
     ті
    0.06
     Voting
    0.06
     steadily
    0.06
    スコ
    0.06
    Act Density 0.005%

    No Known Activations