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

    Neuronpedia

    INDEX
    Explanations

    jail

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    uen
    -0.07
     thou
    -0.07
    _macros
    -0.06
    361
    -0.06
    Medium
    -0.06
    .Slf
    -0.06
    Gold
    -0.06
     goodbye
    -0.06
    amb
    -0.06
     puzzle
    -0.06
    POSITIVE LOGITS
     Tư
    0.08
    问
    0.07
    转
    0.06
    仿
    0.06
     clearTimeout
    0.06
     BadRequest
    0.06
     تحت
    0.06
     notifying
    0.06
     รวม
    0.06
     Entities
    0.06
    Act Density 0.001%

    No Known Activations