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

    Neuronpedia

    INDEX
    Explanations

    movement and location

    np_max-act · gemini-2.0-flash

    The neuron activates on past‐tense verbs ending in “-ed.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     psychiatrist
    -0.07
    _dt
    -0.06
    (exp
    -0.06
     Giang
    -0.06
    lst
    -0.06
     Criteria
    -0.06
     Contractor
    -0.06
    =head
    -0.06
     affidavit
    -0.06
    orent
    -0.06
    POSITIVE LOGITS
     تغ
    0.06
    جمع
    0.06
    Scalars
    0.06
     التص
    0.06
     замі
    0.06
    ẳng
    0.06
     SAY
    0.06
    wake
    0.06
    чива
    0.06
    liš
    0.06
    Act Density 0.159%

    No Known Activations