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

    Neuronpedia

    INDEX
    Explanations

    checking to ensure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     slowly
    0.38
     Slowly
    0.36
    เลย
    0.34
     empezamos
    0.33
     Cir
    0.33
     ripe
    0.32
     מיי
    0.31
    ᱩ
    0.31
    یکشن
    0.31
     empecé
    0.31
    POSITIVE LOGITS
     ensure
    2.98
     ensuring
    2.83
    确保
    2.83
     ensures
    2.78
    Ensure
    2.73
     ensured
    2.70
     Ensure
    2.69
     memastikan
    2.63
    ensure
    2.61
     Ensures
    2.52
    Act Density 0.040%

    No Known Activations