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

    Neuronpedia

    INDEX
    Explanations

    learning math and science

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    iciens
    0.39
    utscher
    0.36
    ães
    0.36
     colorChoice
    0.36
     handset
    0.36
    accompan
    0.34
    Prediction
    0.34
     rasgos
    0.34
    assert
    0.34
    scores
    0.33
    POSITIVE LOGITS
     III
    0.43
     II
    0.41
     Beginners
    0.41
     basics
    0.41
     playlist
    0.40
     beginners
    0.40
    入门
    0.40
     beginner
    0.38
     Beginner
    0.38
     quick
    0.38
    Act Density 0.007%

    No Known Activations