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

    Neuronpedia

    INDEX
    Explanations

    most prominent

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ermöglicht
    0.51
     ermöglichen
    0.43
     anomalies
    0.40
     résulte
    0.40
    ល់
    0.39
     anomalous
    0.39
     construye
    0.39
    Column
    0.39
     परि
    0.39
     بیماری
    0.39
    POSITIVE LOGITS
     byť
    0.46
    use
    0.44
     فيه
    0.43
    ᴼ
    0.41
     ine
    0.40
     RSI
    0.40
    Founder
    0.39
    cha
    0.39
    estar
    0.38
    地元
    0.38
    Act Density 0.001%

    No Known Activations