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

    Neuronpedia

    INDEX
    Explanations

    scene or code structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    nä
    0.71
     aru
    0.71
    dit
    0.67
     Fabric
    0.67
    stärke
    0.67
    aq
    0.67
    arno
    0.66
    landish
    0.66
     ώστε
    0.65
     přímo
    0.65
    POSITIVE LOGITS
    を探
    0.78
     समय
    0.75
     Kishore
    0.74
    𝑺
    0.72
     பணியா
    0.72
    もちろん
    0.71
    います
    0.71
     paiement
    0.71
    Ҭ
    0.70
    VERTISEMENT
    0.70
    Act Density 0.001%

    No Known Activations