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

    Neuronpedia

    INDEX
    Explanations

    digits

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    总额
    -0.07
     Independent
    -0.07
    ائي
    -0.07
    ⊇
    -0.06
     Goldberg
    -0.06
     Cindy
    -0.06
    总面积
    -0.06
    GLfloat
    -0.06
     GLfloat
    -0.06
     Clown
    -0.06
    POSITIVE LOGITS
    Fix
    0.07
     outra
    0.07
     Social
    0.06
     bug
    0.06
     "/";↵
    0.06
     ripping
    0.06
     \
↵
    0.06
     Essays
    0.06
     diğer
    0.06
    ausal
    0.06
    Act Density 0.014%

    No Known Activations