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

    Neuronpedia

    INDEX
    Explanations

    quotation marks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ви
    0.44
    </u>
    0.43
    ico
    0.42
    לי
    0.41
     Bott
    0.41
    ریت
    0.40
    ate
    0.40
    р
    0.40
    ეტ
    0.39
     грудня
    0.38
    POSITIVE LOGITS
     POSSIBLE
    0.48
     histologic
    0.47
     frameN
    0.47
    ponents
    0.46
    न्दावन
    0.45
    ദ്യ
    0.45
     frågor
    0.44
     allyl
    0.44
     ofte
    0.44
     synov
    0.44
    Act Density 0.001%

    No Known Activations