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

    Neuronpedia

    INDEX
    Explanations

    types and generic parameters in class definitions

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

    generics and foreign words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SBATCH
    -0.60
     betweenstory
    -0.60
    ImageContext
    -0.59
     '\\;'
    -0.59
     ब्रेकडाउन
    -0.57
    InputBorder
    -0.53
    دانشنامهٔ
    -0.53
    abstractmethod
    -0.52
    WithIOException
    -0.51
    extAlignment
    -0.50
    POSITIVE LOGITS
     resourceCulture
    0.40
     kvinder
    0.39
     Jugendliche
    0.38
     lidí
    0.35
    Джерела
    0.35
    Slf
    0.35
     людини
    0.35
     ljudi
    0.34
    <bos>
    0.34
     osób
    0.34
    Act Density 0.019%

    No Known Activations