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

    Neuronpedia

    INDEX
    Explanations

    table separators and 'Configuration'

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    твы
    0.83
    いた
    0.80
    defeated
    0.72
    &=&
    0.71
    біць
    0.71
    ್‌
    0.70
    대를
    0.70
    toothpaste
    0.70
     Quadrupèdes
    0.70
    ном
    0.69
    POSITIVE LOGITS
    u
    0.93
    in
    0.93
    ↵
    0.87
     in
    0.83
     potenti
    0.80
    b
    0.74
    l
    0.72
    :
    0.71
    o
    0.71
    i
    0.70
    Act Density 0.041%

    No Known Activations