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

    Neuronpedia

    INDEX
    Explanations

    american followed by entities and concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ট
    1.09
    b
    1.05
     Own
    1.05
     ′
    1.03
     trouverez
    1.01
    دی
    1.01
    вим
    1.01
    bbe
    1.00
    gender
    0.99
     accedere
    0.99
    POSITIVE LOGITS
     Serikat
    1.40
    ization
    1.25
     Samoa
    1.21
    isation
    1.18
    ة
    1.13
    ızı
    1.05
    isasi
    1.05
     sper
    1.02
    ism
    1.01
    ize
    1.01
    Act Density 0.045%

    No Known Activations