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

    Neuronpedia

    INDEX
    Explanations

    Inventions solving a problem

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    艋
    -0.07
    RuntimeObject
    -0.07
    _tracks
    -0.07
    颧
    -0.07
    SCALE
    -0.07
    🥗
    -0.07
    .userAgent
    -0.06
     успех
    -0.06
     theta
    -0.06
    центр
    -0.06
    POSITIVE LOGITS
     Bukkit
    0.08
    Tbl
    0.07
     sanitize
    0.07
     Cleanup
    0.07
    适合
    0.07
    🔀
    0.07
     park
    0.07
    强化
    0.07
    抵达
    0.07
    涧
    0.07
    Act Density 0.072%

    No Known Activations