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

    Neuronpedia

    INDEX
    Explanations

    Icon

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     MAY
    -0.07
     Opt
    -0.07
     Swimming
    -0.06
    危险
    -0.06
     bagi
    -0.06
     unter
    -0.06
    往
    -0.06
    (IO
    -0.06
     Hay
    -0.06
    保证
    -0.06
    POSITIVE LOGITS
     slice
    0.08
    贝壳
    0.08
    .isOn
    0.07
    ѳ
    0.07
    썰
    0.07
    �
    0.07
    喈
    0.07
    嬛
    0.06
     twist
    0.06
    Continue
    0.06
    Act Density 0.018%

    No Known Activations