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

    Neuronpedia

    INDEX
    Explanations

    App menu navigation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tz
    -0.07
     lantern
    -0.07
    Ray
    -0.07
     cannons
    -0.07
    นอกจาก
    -0.07
    阑
    -0.06
    (cls
    -0.06
     doubt
    -0.06
    🚦
    -0.06
     Smoke
    -0.06
    POSITIVE LOGITS
    ))↵
    0.07
    xmin
    0.07
    ('"
    0.07
     Veronica
    0.07
    ">'↵
    0.06
    ציפ
    0.06
    /span
    0.06
     Kevin
    0.06
     新
    0.06
    と共
    0.06
    Act Density 0.015%

    No Known Activations