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

    Neuronpedia

    INDEX
    Explanations

    web

    np_max-act · gemini-2.0-flash

    The neuron fires on mentions of the World Wide Web and related hypertext/web‐protocol terms (e.g. “Web,” “WWW,” “hypertext,” “HTTP,” “HTML”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _sz
    -0.07
    _frag
    -0.07
     preparations
    -0.06
     barn
    -0.06
    etri
    -0.06
     memories
    -0.06
    _buff
    -0.06
    creation
    -0.06
     interactions
    -0.06
    Metric
    -0.06
    POSITIVE LOGITS
     pione
    0.07
     Держав
    0.06
     utilizando
    0.06
     Jerome
    0.06
    0.06
     图
    0.06
     кредит
    0.06
    采用
    0.06
     要
    0.06
     工
    0.06
    Act Density 0.007%

    No Known Activations