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

    Neuronpedia

    INDEX
    Explanations

    articles/forms of "to be"

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    QRSTUVWXYZ
    -0.07
    (Long
    -0.07
     Replica
    -0.07
    (rs
    -0.07
     transporter
    -0.07
    的角色
    -0.07
    logger
    -0.06
    二楼
    -0.06
     gp
    -0.06
    耢
    -0.06
    POSITIVE LOGITS
     Baltic
    0.08
    _LOOK
    0.07
    !!!!
    0.07
     );
↵
↵
    0.07
    ➝
    0.07
     inconsistency
    0.07
     англи
    0.07
    atLng
    0.07
    𬤇
    0.07
     kaynağı
    0.06
    Act Density 0.071%

    No Known Activations