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

    Neuronpedia

    INDEX
    Explanations

    showing or describing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Number
    0.48
    son
    0.48
    Passport
    0.47
    pal
    0.46
    s
    0.46
    คุณ
    0.46
    have
    0.45
    you
    0.45
    Painting
    0.45
    кол
    0.45
    POSITIVE LOGITS
     audits
    0.49
     powders
    0.46
     reefs
    0.46
     enormes
    0.46
     outsiders
    0.45
     orbits
    0.45
     closeModal
    0.45
     booms
    0.45
     불구
    0.44
     bitmaps
    0.44
    Act Density 0.000%

    No Known Activations