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

    Neuronpedia

    INDEX
    Explanations

    chess board represented

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     reintroduced
    0.53
    man
    0.50
    li
    0.49
     প্রযুক্তি
    0.48
    motif
    0.48
     revamp
    0.47
    tracking
    0.47
     revamped
    0.46
    her
    0.45
    tr
    0.45
    POSITIVE LOGITS
    ’.
    0.50
     पढ़ाई
    0.49
    ровки
    0.49
     amelyek
    0.47
     oatmeal
    0.46
    тся
    0.44
     одним
    0.44
    aschen
    0.44
     a
    0.43
    atoren
    0.43
    Act Density 0.000%

    No Known Activations