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

    Neuronpedia

    INDEX
    Explanations

    observations of people

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    brane
    -0.08
    attended
    -0.07
    роме
    -0.06
    ,function
    -0.06
     lect
    -0.06
     lectures
    -0.06
    礼
    -0.06
    uator
    -0.06
    았다
    -0.06
    _transaction
    -0.06
    POSITIVE LOGITS
    Limit
    0.07
    +y
    0.06
     paren
    0.06
     πο
    0.06
     영어
    0.06
    =v
    0.06
     Quyết
    0.06
     услуг
    0.06
     цент
    0.06
    omite
    0.06
    Act Density 0.012%

    No Known Activations