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

    Neuronpedia

    INDEX
    Explanations

    with

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     आग
    -0.07
     fav
    -0.07
     Immun
    -0.06
     indispensable
    -0.06
    ег
    -0.06
    補
    -0.06
    _not
    -0.06
    Good
    -0.06
    executor
    -0.06
    ╝
    -0.06
    POSITIVE LOGITS
    _YELLOW
    0.08
    .smart
    0.07
     Trigger
    0.07
     cotton
    0.07
    (em
    0.07
    ющим
    0.07
     $('#
    0.07
    信息
    0.06
    ")),↵
    0.06
     oleh
    0.06
    Act Density 0.003%

    No Known Activations