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
     Bernardino
    -0.07
     Sweet
    -0.07
    ерб
    -0.07
    unt
    -0.06
     trắng
    -0.06
    еру
    -0.06
    ADIO
    -0.06
    -ag
    -0.06
     Sweat
    -0.06
     knives
    -0.06
    POSITIVE LOGITS
    하였다
    0.07
     halde
    0.06
     сю
    0.06
     معروف
    0.06
    Analy
    0.06
     vybav
    0.06
    485
    0.06
    .interface
    0.06
    upply
    0.06
    Interfaces
    0.06
    Act Density 0.006%

    No Known Activations