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

    Neuronpedia

    INDEX
    Explanations

    sucrose decomposition or properties

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    g
    0.70
    ing
    0.69
    ING
    0.69
     for
    0.63
    .
    0.61
    ার
    0.60
    <0x80>
    0.59
    ă
    0.56
    ির
    0.56
    ة
    0.56
    POSITIVE LOGITS
    рия
    0.63
    abilir
    0.60
    acées
    0.57
    lüğ
    0.57
    ड़िया
    0.57
    hares
    0.57
    ]$-
    0.56
    coproteins
    0.56
    )،
    0.55
    愎
    0.55
    Act Density 0.001%

    No Known Activations