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

    Neuronpedia

    INDEX
    Explanations

    range

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    TB
    -0.07
    /big
    -0.07
    ION
    -0.07
    �
    -0.07
    REA
    -0.07
    比亚迪
    -0.07
    سنة
    -0.07
    ROS
    -0.06
     diz
    -0.06
    IONS
    -0.06
    POSITIVE LOGITS
    _func
    0.07
     handy
    0.06
    ؍
    0.06
     Смотр
    0.06
     gala
    0.06
     Possibly
    0.06
    艚
    0.06
     Chic
    0.06
    .#
    0.06
     découvert
    0.06
    Act Density 0.003%

    No Known Activations