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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash

    The neuron fires on the little greeting or self‐introduction lines (e.g. “Hi!”, “Hello,” “Once again,” “Welcome,” etc.) that kick off the author bio/About Me sections.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Batman
    -0.07
    ynomials
    -0.07
     fantas
    -0.07
    lerden
    -0.06
    озд
    -0.06
     specifics
    -0.06
    "Our
    -0.06
    Batman
    -0.06
    inda
    -0.06
    남
    -0.06
    POSITIVE LOGITS
    toggleClass
    0.07
     Dies
    0.07
    -animate
    0.06
    ливість
    0.06
     سی
    0.06
     बढ़
    0.06
    _tel
    0.06
    .oauth
    0.06
    シ
    0.06
    (relative
    0.06
    Act Density 0.030%

    No Known Activations