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

    Neuronpedia

    INDEX
    Explanations

    lists

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     шп
    -0.07
     Obs
    -0.07
     Vz
    -0.07
     Gat
    -0.06
    ,ID
    -0.06
     incess
    -0.06
     authToken
    -0.06
     inflated
    -0.06
     дис
    -0.06
     lưu
    -0.06
    POSITIVE LOGITS
    July
    0.06
    按
    0.06
    板
    0.06
    -re
    0.06
    ull
    0.06
    uggested
    0.06
    禁止
    0.06
    支援
    0.06
     Root
    0.06
    ordon
    0.06
    Act Density 0.001%

    No Known Activations