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

    Neuronpedia

    INDEX
    Explanations

    :

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     özellikle
    -0.07
    еної
    -0.07
     ナ
    -0.07
    cult
    -0.06
     adds
    -0.06
     nghi
    -0.06
     kır
    -0.06
     faithfully
    -0.06
     лак
    -0.06
     레벨
    -0.06
    POSITIVE LOGITS
    UTO
    0.07
    Neighbor
    0.07
    userId
    0.06
    Better
    0.06
     Goddess
    0.06
    boats
    0.06
    sınız
    0.06
    PER
    0.06
    indow
    0.06
     Mitgli
    0.06
    Act Density 0.007%

    No Known Activations