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

    Neuronpedia

    INDEX
    Explanations

    competition or experience

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ’।
    0.51
    した
    0.46
    ขอ
    0.46
    離
    0.43
    </th>
    0.43
    циями
    0.43
     lím
    0.42
    な
    0.42
    ”।
    0.42
     inhuman
    0.42
    POSITIVE LOGITS
    amet
    0.50
     Caught
    0.49
     to
    0.46
     UserId
    0.46
     Ressourcen
    0.46
     audacity
    0.46
     workout
    0.45
    ارات
    0.45
     revised
    0.45
     Identifier
    0.44
    Act Density 0.001%

    No Known Activations