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

    Neuronpedia

    INDEX
    Explanations

    practice guidelines and exams

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    nsen
    0.44
    lassen
    0.42
    ्न
    0.42
    StringType
    0.42
    ानीय
    0.41
     पैर
    0.38
     frm
    0.38
     woody
    0.37
     plazo
    0.37
    Morgan
    0.37
    POSITIVE LOGITS
     Makes
    0.61
     Practices
    0.52
    Makes
    0.52
    es
    0.52
    makes
    0.50
     Exams
    0.50
     practices
    0.50
    icing
    0.50
    躬
    0.50
    practice
    0.49
    Act Density 0.012%

    No Known Activations