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

    Neuronpedia

    INDEX
    Explanations

    answer whether

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     další
    0.45
    ្អ
    0.41
     commandBuffer
    0.41
    瘾
    0.40
     kilómetros
    0.40
     további
    0.40
    們
    0.40
     Ángeles
    0.39
    Pues
    0.39
     الترك
    0.39
    POSITIVE LOGITS
     ৩
    0.55
     licences
    0.51
     Licence
    0.51
     licence
    0.49
    USH
    0.48
     ۳
    0.46
    графія
    0.46
     privatization
    0.45
     \%
    0.45
     рэгістрацыі
    0.45
    Act Density 0.003%

    No Known Activations