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

    Neuronpedia

    INDEX
    Explanations

    clause preceding

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    在
    0.51
    龙
    0.47
    د
    0.46
    نز
    0.46
     Estable
    0.46
    刚
    0.44
    还是
    0.43
     envío
    0.43
    ب
    0.43
    ῎
    0.42
    POSITIVE LOGITS
    IT
    0.46
     anul
    0.44
     cikin
    0.43
    W
    0.43
    Ala
    0.43
    ইল
    0.43
    fek
    0.43
     noin
    0.42
    IA
    0.41
     ihop
    0.41
    Act Density 0.000%

    No Known Activations