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

    Neuronpedia

    INDEX
    Explanations

    text cleaning

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _keyword
    -0.09
     blindness
    -0.08
     Vern
    -0.08
     forgiveness
    -0.08
     maju
    -0.08
    .Keyword
    -0.08
    ынша
    -0.08
    бур
    -0.08
    һына
    -0.08
    A级
    -0.08
    POSITIVE LOGITS
     deterior
    0.08
     artifacts
    0.08
     Outputs
    0.08
     electronics
    0.07
     possa
    0.07
     calculators
    0.07
     чему
    0.07
     messy
    0.07
     سج
    0.07
     Joint
    0.07
    Act Density 0.002%

    No Known Activations