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

    Neuronpedia

    INDEX
    Explanations

    ras

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ᬕ
    -0.07
     комнат
    -0.07
     afterward
    -0.07
     magnificent
    -0.06
    ◝
    -0.06
    施行
    -0.06
    做到了
    -0.06
     ينبغي
    -0.06
     сегодня
    -0.06
     clums
    -0.06
    POSITIVE LOGITS
    ]("
    0.07
    热搜
    0.07
    请假
    0.06
    pressor
    0.06
    acers
    0.06
    VERN
    0.06
     Opposition
    0.06
    Cou
    0.06
     recruitment
    0.06
    Het
    0.06
    Act Density 0.006%

    No Known Activations