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

    Neuronpedia

    INDEX
    Explanations

    Article titles/content

    np_max-act · gemini-2.0-flash

    The neuron detects section or article headings—i.e. title‐case phrases (often proper names) followed by a colon.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ि,
    -0.07
     {}));↵
    -0.07
    colon
    -0.06
    ệnh
    -0.06
     Rück
    -0.06
    ário
    -0.06
    oyo
    -0.06
    戏
    -0.06
    mod
    -0.06
    _GENERIC
    -0.06
    POSITIVE LOGITS
    (Boolean
    0.07
     STM
    0.07
     anchor
    0.06
    Active
    0.06
     glacier
    0.06
     boyut
    0.06
     Acrobat
    0.06
    _BU
    0.06
    Inflater
    0.06
     smooth
    0.06
    Act Density 0.127%

    No Known Activations