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

    Neuronpedia

    INDEX
    Explanations

    references to algorithms and programming concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    following "Eg" or similar two-letter sequences

    np_acts-logits-general · gemini-2.0-flash

    eg / Arg / Leg / Berg + common suffixes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    oma
    -0.66
    webElementXpaths
    -0.64
    surfaces
    -0.64
    oss
    -0.58
    er
    -0.57
    ova
    -0.57
    ovski
    -0.56
    uta
    -0.55
     better
    -0.54
    Pax
    -0.54
    POSITIVE LOGITS
    standers
    0.55
    hemiah
    0.51
    didSet
    0.50
     craindre
    0.50
    最快更新
    0.47
     perju
    0.47
     useHistory
    0.46
    WriteLiteral
    0.46
     ujednoznacz
    0.45
    Extinguishing
    0.45
    Act Density 0.266%

    No Known Activations