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

    Neuronpedia

    INDEX
    Explanations

    code headers and copyright

    np_max-act · gemini-2.0-flash

    The neuron detects lines of comment‐block metadata—e.g. the leading “/*” license or copyright header lines in source code.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     HID
    -0.07
     unordered
    -0.06
    _Internal
    -0.06
    ＝
    -0.06
    .Linear
    -0.06
     satire
    -0.06
    ném
    -0.06
          
    -0.06
    .dispatch
    -0.06
    НО
    -0.06
    POSITIVE LOGITS
    раст
    0.08
    cold
    0.07
     mapa
    0.07
    -inf
    0.07
     hoop
    0.06
    POINTS
    0.06
     grandes
    0.06
     بگ
    0.06
     된다
    0.06
     Ein
    0.06
    Act Density 0.003%

    No Known Activations