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

    Neuronpedia

    INDEX
    Explanations

    legal ethics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _prec
    -0.08
    車
    -0.07
    .PO
    -0.07
    avorite
    -0.06
    ขาว
    -0.06
    摘编
    -0.06
    ities
    -0.06
    饼干
    -0.06
     Еще
    -0.06
    ivities
    -0.06
    POSITIVE LOGITS
    _RED
    0.07
    用于
    0.07
    启动
    0.06
    _handles
    0.06
     Chapel
    0.06
    ☡
    0.06
     Vanguard
    0.06
     overwhelm
    0.06
    ﬠ
    0.06
    Play
    0.06
    Act Density 0.015%

    No Known Activations