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

    Neuronpedia

    INDEX
    Explanations

    locations

    np_max-act · gemini-2.0-flash

    names of locations or geographic entities.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     lasted
    -0.07
    Seen
    -0.06
     efforts
    -0.06
     علی
    -0.06
     cores
    -0.06
    arring
    -0.06
    acre
    -0.06
     مجموعه
    -0.06
     Roger
    -0.06
    _fh
    -0.06
    POSITIVE LOGITS
     
    0.07
    =batch
    0.07
     sofa
    0.07
     BusinessException
    0.07
    سة
    0.07
    (strict
    0.07
     норм
    0.07
    нен
    0.06
    频
    0.06
     همکاری
    0.06
    Act Density 0.002%

    No Known Activations