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

    Neuronpedia

    INDEX
    Explanations

    the problem:

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     knowing
    0.45
    するので
    0.39
     in
    0.38
     enzyme
    0.37
    るので
    0.37
     ஊராட்சி
    0.36
    ます
    0.36
     thấy
    0.36
     Enzyme
    0.36
     kindred
    0.36
    POSITIVE LOGITS
     frühen
    0.42
     lokalen
    0.42
    迤
    0.42
    цыя
    0.41
     उदय
    0.41
     대신
    0.41
     اصلي
    0.41
     विष
    0.40
     früheren
    0.40
     अक्षय
    0.40
    Act Density 0.007%

    No Known Activations