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

    Neuronpedia

    INDEX
    Explanations

    string matching

    np_max-act · gemini-2.0-flash

    The neuron fires on code that performs string matching or substring‐testing operations.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    technical discussions surrounding coding and programming issues.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     yourself
    -0.07
     ヴ
    -0.06
    (be
    -0.06
     изуч
    -0.06
     polys
    -0.06
     selves
    -0.06
     Dodgers
    -0.06
     influenced
    -0.06
     Cultural
    -0.06
     Ice
    -0.06
    POSITIVE LOGITS
     impairment
    0.07
     eben
    0.07
     ayrıntılı
    0.07
    ISTER
    0.07
    .Program
    0.07
     rond
    0.06
     habil
    0.06
    .main
    0.06
    .optimizer
    0.06
    ByUsername
    0.06
    Act Density 0.021%

    No Known Activations