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

    Neuronpedia

    INDEX
    Explanations

    Brackets

    np_max-act · gemini-2.0-flash

    Detects embedded image/attachment markup and associated file metadata (lines that indicate attachments, image tags, filenames and size/byte information).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Negative Logits
    免
    -0.08
     AAC
    -0.07
    an
    -0.06
    ove
    -0.06
    虑
    -0.06
     tone
    -0.06
    ूर
    -0.06
     morphology
    -0.06
    tickets
    -0.06
     موضوع
    -0.06
    POSITIVE LOGITS
    (model
    0.07
     "_
    0.07
     resembl
    0.07
     Arrow
    0.06
    otate
    0.06
     babes
    0.06
     Leads
    0.06
    ceased
    0.06
     IEEE
    0.06
    .isArray
    0.06
    Act Density 0.070%

    No Known Activations