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

    Neuronpedia

    INDEX
    Explanations

    score

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Program
    0.91
    PROGRAM
    0.79
    program
    0.78
     Program
    0.77
     programma
    0.76
     programmi
    0.76
    programa
    0.76
     programa
    0.75
    Pan
    0.73
     कार्यक्रमा
    0.71
    POSITIVE LOGITS
     score
    0.74
     scorer
    0.70
     Score
    0.67
    分
    0.65
    iffe
    0.65
    滾
    0.64
    score
    0.64
    ቀ
    0.64
    <body>
    0.63
    得分
    0.63
    Act Density 0.019%

    No Known Activations