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

    Neuronpedia

    INDEX
    Explanations

    license

    np_max-act · gemini-2.0-flash

    The neuron fires on code‐style license headers—detecting the comment markers and keywords (e.g. “/*”, “@license”, “magnet:?xt=…”, “GPL-v2”) that signal a software‐license block.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    HTML document structure elements.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    TION
    -0.07
     Metodo
    -0.07
     trajectories
    -0.07
    appear
    -0.07
    _func
    -0.07
    ейн
    -0.07
    conversation
    -0.06
     Ris
    -0.06
    アニメ
    -0.06
    "N
    -0.06
    POSITIVE LOGITS
    여
    0.07
     áp
    0.07
    ồi
    0.06
     adamant
    0.06
     양
    0.06
     여
    0.06
    压
    0.06
    ornecedor
    0.06
     vyd
    0.06
    otyping
    0.06
    Act Density 0.000%

    No Known Activations