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

    Neuronpedia

    INDEX
    Explanations

    ://

    np_max-act · gemini-2.0-flash

    The neuron detects pieces of URLs (e.g. protocol prefixes, domain names, and separators) within link or image markdown.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     employees
    -0.08
     dbl
    -0.07
    Styled
    -0.07
     Méd
    -0.07
    opens
    -0.06
     men
    -0.06
     MEN
    -0.06
    aph
    -0.06
     Discount
    -0.06
     maternal
    -0.06
    POSITIVE LOGITS
    Degree
    0.07
    趣
    0.06
    (ds
    0.06
     LinearGradient
    0.06
    .Error
    0.06
    }\"
    0.06
     Sally
    0.06
     Venice
    0.06
     wreak
    0.06
     Без
    0.06
    Act Density 0.009%

    No Known Activations