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

    Neuronpedia

    INDEX
    Explanations

    javascript code documentation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ке
    1.23
    ה
    1.20
    鹉
    1.15
    anity
    1.05
     समित
    1.04
     godina
    1.02
    ють
    1.00
    CHESTER
    1.00
    тия
    1.00
    ➺
    1.00
    POSITIVE LOGITS
     colloquial
    1.19
    ió
    1.17
    arak
    1.15
    nt
    1.14
    idi
    1.13
     esso
    1.07
    보니
    1.07
     obowiąz
    1.06
    mov
    1.05
    ことで
    1.04
    Act Density 0.002%

    No Known Activations