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

    Neuronpedia

    INDEX
    Explanations

    math and science worksheets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     cryptographic
    0.52
    orcid
    0.47
     physicochemical
    0.46
     equivariant
    0.46
    俾
    0.46
     OAuth
    0.45
     alegre
    0.45
     इंदिरा
    0.44
     langchain
    0.44
     biliary
    0.44
    POSITIVE LOGITS
     BONUS
    0.57
     Bonus
    0.56
     Answers
    0.55
     circle
    0.54
     answers
    0.54
    练习
    0.51
     आंसर
    0.51
     worksheet
    0.51
     Hint
    0.51
     Worksheet
    0.50
    Act Density 0.004%

    No Known Activations