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

    Neuronpedia

    INDEX
    Explanations

    problem

    np_max-act · gemini-2.0-flash

    technical language related to algorithms and data structures in graph theory.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ェ
    -0.06
    ams
    -0.06
     cores
    -0.06
     完
    -0.06
    	pool
    -0.06
    _successful
    -0.06
    _ts
    -0.05
    diff
    -0.05
    enh
    -0.05
    _Collections
    -0.05
    POSITIVE LOGITS
    "]
↵
    0.07
     oku
    0.07
    asctime
    0.06
     moot
    0.06
     základní
    0.06
    Representation
    0.06
     Probability
    0.06
    (Message
    0.06
    λέον
    0.06
     Teknik
    0.06
    Act Density 0.075%

    No Known Activations