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

    Neuronpedia

    INDEX
    Explanations

    cannot fulfill requests

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Oriented
    0.73
    ngths
    0.70
     ಅವಕಾಶ
    0.67
    ಂಕ
    0.62
    ್ಯೂ
    0.62
    트는
    0.61
    ಂಪ
    0.60
    푞
    0.60
     Incluso
    0.59
    스는
    0.59
    POSITIVE LOGITS
    ↵
    1.00
    an
    0.83
     إلا
    0.64
     time
    0.63
     name
    0.62
     едно
    0.62
    :
    0.62
     dieser
    0.60
     спи
    0.58
     l
    0.57
    Act Density 0.597%

    No Known Activations