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

    Neuronpedia

    INDEX
    Explanations

    alternate history

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     oils
    -0.08
     fiesta
    -0.08
     irritation
    -0.08
     nuisance
    -0.08
     lotions
    -0.08
     irritated
    -0.08
     одежды
    -0.08
    油
    -0.08
    Foto
    -0.08
     beverages
    -0.07
    POSITIVE LOGITS
     downfall
    0.09
     imaginar
    0.08
     Outcomes
    0.08
    Ux
    0.08
    未来
    0.08
    ēm
    0.08
     Left
    0.08
     Founder
    0.08
     прошл
    0.08
     WWII
    0.08
    Act Density 0.065%

    No Known Activations