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

    Neuronpedia

    INDEX
    Explanations

    Wembley

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Damn
    -0.07
     Krishna
    -0.06
     aktual
    -0.06
     ян
    -0.06
     fries
    -0.06
    ไร
    -0.06
     Vision
    -0.06
    初始化
    -0.06
     azimuth
    -0.06
    岩
    -0.05
    POSITIVE LOGITS
    _ASC
    0.07
     verso
    0.07
    .CreateTable
    0.07
     hairs
    0.07
    generic
    0.07
    afd
    0.06
     Vent
    0.06
     şey
    0.06
    stashop
    0.06
     IOC
    0.06
    Act Density 0.005%

    No Known Activations