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

    Neuronpedia

    INDEX
    Explanations

    Programming/coding

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of software library or package names (e.g. Paperclip, ParaView, tmux, Sidekiq, Resque) in code or documentation.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     flair
    -0.07
    "Do
    -0.07
    ourced
    -0.07
     search
    -0.07
    BILE
    -0.06
     piss
    -0.06
    建設
    -0.06
    ขว
    -0.06
    getStringExtra
    -0.06
    AspectRatio
    -0.06
    POSITIVE LOGITS
    阅读
    0.07
     gle
    0.06
    peaker
    0.06
     diminished
    0.06
     Fast
    0.06
    Fast
    0.06
    boss
    0.06
     pageTitle
    0.06
     Heidi
    0.06
     allen
    0.06
    Act Density 0.117%

    No Known Activations