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

    Neuronpedia

    INDEX
    Explanations

    all, every

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     noises
    -0.06
     limitation
    -0.06
     Pollution
    -0.06
    Dto
    -0.06
    ITLE
    -0.06
     ，
    -0.06
     医
    -0.06
     Alerts
    -0.06
     ще
    -0.06
     ún
    -0.06
    POSITIVE LOGITS
    ENE
    0.07
    anged
    0.07
    .Reverse
    0.06
     IMPORTANT
    0.06
    씩
    0.06
    argin
    0.06
     Promo
    0.06
     crafting
    0.06
     unwilling
    0.06
     patio
    0.06
    Act Density 0.003%

    No Known Activations