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

    Neuronpedia

    INDEX
    Explanations

    study

    np_max-act · gemini-2.0-flash

    This neuron specifically detects the occurrence of the word “study,” especially when introducing or describing a research study.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     eclipse
    -0.07
     imap
    -0.06
     evrop
    -0.06
    دان
    -0.06
    .TABLE
    -0.06
     ern
    -0.06
     přítom
    -0.06
    ================================================
    -0.06
     sic
    -0.06
     attendant
    -0.06
    POSITIVE LOGITS
    라도
    0.07
    няет
    0.07
     المغ
    0.07
    оф
    0.06
     grop
    0.06
    urs
    0.06
    Div
    0.06
     altro
    0.06
    hyp
    0.06
    Through
    0.06
    Act Density 0.014%

    No Known Activations