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

    Neuronpedia

    INDEX
    Explanations

    references to academic papers and reviews in scientific contexts

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

    scientific paper reviews

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ########.
    -0.62
    WithIOException
    -0.61
     OMITBAD
    -0.59
    rungsseite
    -0.58
     wireType
    -0.57
    +#+#
    -0.49
    UserScript
    -0.49
    transQ
    -0.46
    rawDesc
    -0.44
    TargetException
    -0.44
    POSITIVE LOGITS
    faatkan
    0.40
    vedať
    0.39
     jengibre
    0.38
     يتيمه
    0.37
     vectorielle
    0.37
    ilish
    0.37
     marins
    0.36
     defStyleAttr
    0.36
     Catalana
    0.35
    lösung
    0.35
    Act Density 0.186%

    No Known Activations