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

    Neuronpedia

    INDEX
    Explanations

    tables and statistics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Jako
    -0.08
    ZO
    -0.07
     parsers
    -0.06
     bib
    -0.06
     Так
    -0.06
    Ｙ
    -0.06
    RESSION
    -0.06
     sicher
    -0.06
    ])↵↵
    -0.06
     =",
    -0.06
    POSITIVE LOGITS
    .Free
    0.07
    补
    0.07
    �장
    0.07
    ुध
    0.07
    赵
    0.06
     carbohydrates
    0.06
    šem
    0.06
     زیبا
    0.06
     پي
    0.06
     illustrated
    0.06
    Act Density 0.001%

    No Known Activations