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

    Neuronpedia

    INDEX
    Explanations

    code and quotes

    np_max-act · gemini-2.0-flash

    descriptive phrases about the company's operational strengths and commitments.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    It detects tokens that are part of the company’s name (i.e. the proper‐noun brand name at the start of the introduction).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     eh
    -0.07
    _file
    -0.07
     DB
    -0.06
    _input
    -0.06
     dairy
    -0.06
     appetite
    -0.06
     Orta
    -0.06
    	img
    -0.06
     seaw
    -0.06
    لت
    -0.06
    POSITIVE LOGITS
    рун
    0.07
     combineReducers
    0.07
    (numero
    0.07
    П
    0.07
    .TypeOf
    0.06
     DOI
    0.06
    .fake
    0.06
     salope
    0.06
    -muted
    0.06
    авис
    0.06
    Act Density 0.028%

    No Known Activations