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

    Neuronpedia

    INDEX
    Explanations

    xlim and ylim

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Ms
    -0.08
    䴕
    -0.08
     contents
    -0.08
    躬
    -0.07
    鼻
    -0.07
    orphism
    -0.07
     And
    -0.07
    👳
    -0.07
     samo
    -0.06
    tg
    -0.06
    POSITIVE LOGITS
    혔
    0.08
    行动计划
    0.07
    _ylim
    0.07
    附近的
    0.07
    预计
    0.07
    wick
    0.07
    완
    0.07
     refurbished
    0.07
     초
    0.07
    -Tr
    0.07
    Act Density 0.003%

    No Known Activations