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

    Neuronpedia

    INDEX
    Explanations

    URLs and requests

    np_acts-logits-general · gemini-2.5-flash-lite

    phrases that mark user directives or requests (often polite or emphatic) and the conversation’s turn-boundary tokens.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Negative Logits
     grammaticality
    0.49
     LaTeX
    0.47
     schoolchildren
    0.46
     interstitiis
    0.44
     millilit
    0.44
     útiles
    0.44
     alumna
    0.43
    冋
    0.43
     nanom
    0.43
    FileList
    0.42
    POSITIVE LOGITS
    0.66
    https
    0.55
    create
    0.53
    request
    0.52
    here
    0.47
    )
    0.47
    CREATE
    0.47
     https
    0.46
     ,
    0.45
    1
    0.45
    Act Density 0.179%

    No Known Activations