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

    Neuronpedia

    INDEX
    Explanations

    diversity and size

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     neka
    1.40
    升
    1.32
    フォン
    1.28
     atherosclerosis
    1.25
    পত্রে
    1.25
     całość
    1.23
     conter
    1.23
     earthqu
    1.21
     succulents
    1.21
    伒
    1.20
    POSITIVE LOGITS
    ни
    1.36
    in
    1.27
    an
    1.25
    ничный
    1.22
    ad
    1.14
    se
    1.10
    inning
    1.10
    el
    1.09
    te
    1.08
    w
    1.06
    Act Density 0.000%

    No Known Activations