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

    Neuronpedia

    INDEX
    Explanations

    Source

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     受
    -0.06
    .Txt
    -0.06
    (segment
    -0.06
    (generator
    -0.06
    (Current
    -0.06
     changed
    -0.06
     но
    -0.06
     wildfires
    -0.06
     okuy
    -0.06
     answered
    -0.05
    POSITIVE LOGITS
    bitrary
    0.07
     quartz
    0.07
    米
    0.07
    iii
    0.07
    خو
    0.06
    리는
    0.06
    رق
    0.06
     ash
    0.06
     hc
    0.06
    enerator
    0.06
    Act Density 0.005%

    No Known Activations