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

    Neuronpedia

    INDEX
    Explanations

    academic paper, audience, counselor

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    től
    2.25
     وإ
    1.99
    Stderr
    1.99
    ا
    1.99
    tau
    1.98
    اً
    1.95
     أيضاً
    1.91
     eğer
    1.87
     útiles
    1.82
    می
    1.81
    POSITIVE LOGITS
    其他
    2.13
    来越
    2.03
    ER
    1.99
    ors
    1.98
    來越
    1.96
     conifers
    1.93
    하는
    1.84
    Ли
    1.82
    ாவை
    1.81
    िटी
    1.80
    Act Density 0.020%

    No Known Activations