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

    Neuronpedia

    INDEX
    Explanations

    misspelled words

    np_max-act · gemini-2.0-flash

    This neuron detects text that contains many grammatical and spelling errors or instructions asking for intentionally poor/bad grammar.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Negative Logits
    svm
    -0.07
     vague
    -0.07
     tele
    -0.06
    빌
    -0.06
    Ba
    -0.06
    annies
    -0.06
    lookup
    -0.06
     sign
    -0.06
    Trees
    -0.06
     meantime
    -0.06
    POSITIVE LOGITS
    أسلحة
    0.08
    品类
    0.08
    _SENS
    0.08
     aftermarket
    0.07
     plutôt
    0.07
    (isolate
    0.07
    (animated
    0.07
     reopen
    0.07
     erot
    0.07
     calloc
    0.07
    Act Density 0.258%

    No Known Activations