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

    Neuronpedia

    INDEX
    Explanations

    classification

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     instantaneous
    -0.07
     Dark
    -0.07
     Tk
    -0.06
     CSV
    -0.06
     όμως
    -0.06
     Toilet
    -0.06
    θρω
    -0.06
    кта
    -0.06
     LANGUAGE
    -0.06
    มอ
    -0.06
    POSITIVE LOGITS
    .Logging
    0.07
     supervision
    0.07
     hiểm
    0.07
     mip
    0.06
    .ReadInt
    0.06
     imageSize
    0.06
     유
    0.06
     Gibbs
    0.06
     Navigate
    0.06
    shine
    0.06
    Act Density 0.011%

    No Known Activations