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

    Neuronpedia

    INDEX
    Explanations

    models focused

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    وتي
    0.41
    ார்க
    0.41
     निर्देशांक
    0.40
     نسخه
    0.40
     本当
    0.39
     grabar
    0.39
     मौलिक
    0.38
     bens
    0.38
     factorizar
    0.38
     革
    0.38
    POSITIVE LOGITS
     closely
    0.39
     تتح
    0.37
    interval
    0.37
    austral
    0.36
     vic
    0.36
    aphylococcus
    0.36
     unexpected
    0.35
    Russell
    0.35
    ch
    0.35
    ale
    0.35
    Act Density 0.001%

    No Known Activations