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

    Neuronpedia

    INDEX
    Explanations

    named

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Weight
    -0.07
     usually
    -0.07
     parti
    -0.07
     پی
    -0.07
     Evrop
    -0.06
    zones
    -0.06
     podstat
    -0.06
    butt
    -0.06
    YRO
    -0.06
    .Comp
    -0.06
    POSITIVE LOGITS
     named
    0.08
     naming
    0.07
    arring
    0.06
    名無し
    0.06
     Naming
    0.06
    恐
    0.06
     Narendra
    0.06
    named
    0.06
    vpn
    0.06
    acer
    0.06
    Act Density 0.008%

    No Known Activations