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

    Neuronpedia

    INDEX
    Explanations

    paying attention to detail

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     genom
    1.05
     visar
    1.05
     musik
    1.02
     ruta
    0.99
     at
    0.98
     书
    0.98
     for
    0.96
     {}>,
    0.96
    0.96
    rom
    0.95
    POSITIVE LOGITS
    t
    2.05
    고
    1.79
    ت
    1.63
    c
    1.62
    g
    1.54
    ار
    1.47
    b
    1.42
    ع
    1.35
    ਕ
    1.34
    ৬
    1.33
    Act Density 0.007%

    No Known Activations