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

    Neuronpedia

    INDEX
    Explanations

    JSON schema formats

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     می‌کنند
    0.53
     जांच
    0.51
     التص
    0.50
    ták
    0.47
    ají
    0.47
    该公司
    0.46
    amiento
    0.46
    该
    0.46
    ów
    0.46
    cein
    0.45
    POSITIVE LOGITS
     inser
    0.54
     bize
    0.52
     means
    0.49
     molte
    0.49
    к
    0.49
     schwar
    0.49
    0.48
     messa
    0.48
     FedEx
    0.47
     orice
    0.47
    Act Density 0.000%

    No Known Activations