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

    Neuronpedia

    INDEX
    Explanations

    specific formatting or structure in the text, such as headings or designated sections

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

    Code, math, or unusual symbols

    np_acts-logits-general · gemini-2.0-flash

    defective product

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RegistryLite
    -0.54
    bute
    -0.53
    culaires
    -0.53
    gena
    -0.52
    MemberId
    -0.52
    ναν
    -0.51
    过去的
    -0.50
    erne
    -0.50
     وتسجيلات
    -0.50
    هره
    -0.50
    POSITIVE LOGITS
    enterOuterAlt
    0.72
    abestanden
    0.68
    SaveChangesAsync
    0.66
     insuffisamment
    0.64
    oneofs
    0.58
    encodeWith
    0.58
     onAnimation
    0.57
    WebVitals
    0.57
    DJANGO
    0.56
     setuptools
    0.55
    Act Density 0.073%

    No Known Activations