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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash

    The neuron primarily detects the preposition “in.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    GraphQL
    -0.07
    =Y
    -0.06
     yazılı
    -0.06
    athering
    -0.06
     paramMap
    -0.06
     зі
    -0.06
    errorMsg
    -0.06
    -St
    -0.06
     كار
    -0.06
    _conf
    -0.06
    POSITIVE LOGITS
    ätt
    0.07
     döneminde
    0.07
     όταν
    0.07
     ridiculously
    0.07
    antidad
    0.07
     PVOID
    0.06
    -www
    0.06
    .getDeclared
    0.06
     tratt
    0.06
     CBC
    0.06
    Act Density 0.093%

    No Known Activations