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

    Neuronpedia

    INDEX
    Explanations

    back + context words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     onward
    0.42
     যৌগ
    0.41
     onwards
    0.39
    &=&\
    0.38
     جمهوری
    0.38
     présenté
    0.37
     বুঝতে
    0.37
    ペット
    0.36
     நாம்
    0.36
     Fernanda
    0.36
    POSITIVE LOGITS
     Back
    0.83
    Back
    0.71
    back
    0.70
     назад
    0.68
     BACK
    0.62
     backing
    0.62
    BACK
    0.61
     back
    0.61
    backs
    0.61
    wards
    0.58
    Act Density 0.039%

    No Known Activations