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

    Neuronpedia

    INDEX
    Explanations

    punctuation followed by descriptive words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nowhere
    1.14
     nothing
    1.14
    Nothing
    1.08
     Nothing
    1.07
     Forget
    1.03
    nothing
    1.01
     doves
    0.98
    Forget
    0.98
     NOTHING
    0.98
     miracles
    0.97
    POSITIVE LOGITS
     將
    0.83
     प्रदान
    0.82
     intéressante
    0.82
     zorgt
    0.80
     kullanarak
    0.79
     مبنی
    0.78
     является
    0.77
     مفید
    0.77
     প্রদান
    0.77
    を使用して
    0.76
    Act Density 0.009%

    No Known Activations