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 detects occurrences of “study” in the phrase introducing a paper’s objective (e.g. “the aim of this study was to…”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     헤
    -0.06
    clientId
    -0.06
    _PD
    -0.06
     leggings
    -0.06
    WhatsApp
    -0.06
     TMP
    -0.06
     MediaTek
    -0.06
     teardown
    -0.06
     Initialized
    -0.06
    csr
    -0.06
    POSITIVE LOGITS
     forever
    0.07
     шк
    0.07
     movimiento
    0.06
     money
    0.06
     hall
    0.06
    otty
    0.06
    ходит
    0.06
     Forever
    0.06
    ALLERY
    0.06
     acceptable
    0.06
    Act Density 0.016%

    No Known Activations