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

    Neuronpedia

    INDEX
    Explanations

    webpage column design

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     reimbursement
    -0.08
    匹
    -0.08
     Jack
    -0.08
     totally
    -0.07
    无偿
    -0.07
     ~/
    -0.06
     West
    -0.06
     Đ
    -0.06
    ù
    -0.06
     tableView
    -0.06
    POSITIVE LOGITS
    (pub
    0.07
    бур
    0.07
    fox
    0.06
    ㏱
    0.06
     occurring
    0.06
    샵
    0.06
    consume
    0.06
    YO
    0.06
    垾
    0.06
    _alive
    0.06
    Act Density 0.021%

    No Known Activations