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

    Neuronpedia

    INDEX
    Explanations

    Generative AI

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    此
    0.92
     nonexpansive
    0.91
    ادار
    0.90
    č
    0.87
    roscopic
    0.85
    ুজ
    0.81
    传来
    0.81
    thm
    0.81
    arily
    0.81
    can
    0.81
    POSITIVE LOGITS
    तून
    1.08
     reins
    1.03
    л
    1.02
    0.99
    ्रीय
    0.93
    仲間
    0.91
     économiques
    0.91
    awas
    0.90
    を着
    0.90
    ınız
    0.90
    Act Density 0.222%

    No Known Activations