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

    Neuronpedia

    INDEX
    Explanations

    closing parentheses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    bbero
    1.00
     زمان
    0.87
    Fortunately
    0.86
    ￱
    0.85
    बित
    0.85
    ële
    0.85
    Thankfully
    0.84
    冫
    0.84
     breakthrough
    0.82
    শিকান্ত
    0.82
    POSITIVE LOGITS
     clazz
    1.01
    ust
    0.99
    relatively
    0.95
    なります
    0.95
    이다
    0.95
    sensing
    0.92
     অঞ্জ
    0.91
    ሢ
    0.91
     tirelessly
    0.90
    ক্ক
    0.90
    Act Density 0.001%

    No Known Activations