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

    Neuronpedia

    INDEX
    Explanations

    0

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Clan
    -0.06
     вір
    -0.06
     hiss
    -0.06
    ﺔ
    -0.06
    stripe
    -0.06
     آیا
    -0.06
     Stewart
    -0.06
    etration
    -0.06
     deze
    -0.06
    :size
    -0.06
    POSITIVE LOGITS
     nud
    0.08
    ạy
    0.07
     reco
    0.07
    flatten
    0.07
     MAY
    0.06
     cpp
    0.06
     requ
    0.06
     impuls
    0.06
     مختلف
    0.06
     So
    0.06
    Act Density 0.012%

    No Known Activations