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

    Neuronpedia

    INDEX
    Explanations

    say "-ibility"

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     bağı
    0.55
     வால்
    0.52
     напрямую
    0.52
     загу
    0.51
     адрес
    0.51
     пра
    0.50
     вулка
    0.50
    november
    0.50
    ABAD
    0.50
    🏪
    0.50
    POSITIVE LOGITS
     ib
    2.70
    ible
    2.67
     IB
    2.66
    IB
    2.56
    ibil
    2.55
    ibles
    2.50
    ibl
    2.50
    ib
    2.48
    IBLE
    2.47
    ibility
    2.45
    Act Density 0.084%

    No Known Activations