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

    Neuronpedia

    INDEX
    Explanations

    before

    np_max-act · gemini-2.0-flash

    This neuron detects protocol timing terms in experimental methods, such as “before” and “pretreatment.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     energy
    -0.07
    　　　　　　
    -0.07
    .micro
    -0.07
    EDIT
    -0.07
    _GROUP
    -0.07
    inv
    -0.06
     ############
    -0.06
     =↵↵
    -0.06
    　　　　　　　
    -0.06
    -success
    -0.06
    POSITIVE LOGITS
     ipad
    0.07
     gchar
    0.07
     вся
    0.07
    _AMD
    0.07
    txn
    0.06
     rhet
    0.06
     IconButton
    0.06
     Sharia
    0.06
    ंघ
    0.06
     일본
    0.06
    Act Density 0.011%

    No Known Activations