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

    Neuronpedia

    INDEX
    Explanations

    git

    np_max-act · gemini-2.0-flash

    The neuron fires on parts of package‐manifest JSON that look like URL strings—especially Git repo URLs (e.g. the “git” and “://github.com” tokens).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     skipped
    -0.07
     spre
    -0.06
    .EVT
    -0.06
     하면
    -0.06
    _updates
    -0.06
     Acad
    -0.06
    شمالی
    -0.06
    _WAKE
    -0.06
     FIR
    -0.06
    Stage
    -0.06
    POSITIVE LOGITS
    sgiving
    0.08
     Traditional
    0.07
    .spotify
    0.07
     burger
    0.07
     IPv
    0.07
    orable
    0.06
    ्वप
    0.06
    imony
    0.06
     Thanksgiving
    0.06
    git
    0.06
    Act Density 0.001%

    No Known Activations