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

    Neuronpedia

    INDEX
    Explanations

    different from

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     competitors
    0.45
    isors
    0.43
    ैमर
    0.42
    กับ
    0.42
    iors
    0.41
    ជាមួយ
    0.41
    সাথে
    0.40
    itors
    0.40
    zea
    0.40
     broadcasters
    0.40
    POSITIVE LOGITS
     från
    0.69
     from
    0.63
    จาก
    0.59
    from
    0.58
     от
    0.52
     από
    0.51
     FROM
    0.51
     फ्रॉम
    0.50
     fron
    0.50
     dari
    0.49
    Act Density 0.017%

    No Known Activations