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

    Neuronpedia

    INDEX
    Explanations

    book chapters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    branch
    -0.87
     Branch
    -0.83
    enderror
    -0.81
     chapter
    -0.78
    chapter
    -0.75
     branch
    -0.73
    mybatisplus
    -0.73
     stället
    -0.73
     "..\..\
    -0.70
     varandra
    -0.70
    POSITIVE LOGITS
    e
    0.74
    ing
    0.67
    al
    0.65
     or
    0.61
    ed
    0.60
     of
    0.60
    es
    0.54
    /
    0.54
    '
    0.53
     and
    0.52
    Act Density 0.055%

    No Known Activations