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

    Neuronpedia

    INDEX
    Explanations

    red giant, resource allocation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    which
    0.54
    ت
    0.54
    where
    0.51
    ่
    0.49
     which
    0.48
     where
    0.48
    tips
    0.48
    bike
    0.47
    و
    0.47
    י
    0.46
    POSITIVE LOGITS
    θηκαν
    0.52
     dieron
    0.47
     оружи
    0.47
    óln
    0.46
    ються
    0.46
     каса
    0.46
     воору
    0.46
    лями
    0.46
    ړي
    0.46
    ार्टम
    0.45
    Act Density 0.001%

    No Known Activations