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

    Neuronpedia

    INDEX
    Explanations

    python code comments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    vely
    0.73
    odata
    0.70
    cens
    0.69
    oids
    0.68
     Ubuntu
    0.68
    还可以
    0.67
     különb
    0.66
    ূপে
    0.66
     ষ
    0.66
     akár
    0.66
    POSITIVE LOGITS
    ḩ
    0.62
    гла
    0.59
    暉
    0.58
    OUR
    0.57
    Your
    0.57
     APPRO
    0.56
    Consistent
    0.56
    手
    0.56
    持ち
    0.56
     Establishing
    0.56
    Act Density 0.001%

    No Known Activations