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

    Neuronpedia

    INDEX
    Explanations

    Bacteria

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cà
    -0.07
    枷
    -0.07
    irl
    -0.07
    Camp
    -0.07
    �
    -0.07
    身穿
    -0.07
    乐趣
    -0.07
    licting
    -0.07
     assh
    -0.07
    门店
    -0.07
    POSITIVE LOGITS
    .Gradient
    0.08
    较好的
    0.08
    ски
    0.08
    IDGET
    0.07
     YORK
    0.07
    шка
    0.07
    .TestCase
    0.07
    "}>↵
    0.07
    ULATION
    0.07
     preacher
    0.07
    Act Density 0.001%

    No Known Activations