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

    Neuronpedia

    INDEX
    Explanations

    problem and example

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     brady
    0.44
     Merritt
    0.43
    ไหล
    0.43
     Brady
    0.42
     Keg
    0.41
     Oakland
    0.41
    inar
    0.40
     Schuster
    0.40
    ekra
    0.40
    keits
    0.40
    POSITIVE LOGITS
    题目
    0.76
     submission
    0.72
    題目
    0.69
    submission
    0.68
     제출
    0.68
     submissions
    0.68
     OJ
    0.68
    样例
    0.68
    problem
    0.66
    submissions
    0.66
    Act Density 0.007%

    No Known Activations