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

    Neuronpedia

    INDEX
    Explanations

    contextual definitions like 'E'

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    enteuer
    1.21
    वानगी
    1.14
     Bundan
    1.13
     لذلك
    1.12
     tersedia
    1.10
     bundan
    1.08
    glacial
    1.08
     shady
    1.07
     subsequently
    1.07
     należy
    1.06
    POSITIVE LOGITS
    t
    1.27
    पर
    1.09
    র
    1.04
    rę
    1.04
     George
    1.03
    ا
    1.00
    Identifier
    0.98
     Gonz
    0.97
    সিক
    0.97
    臾
    0.95
    Act Density 0.003%

    No Known Activations