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

    Neuronpedia

    INDEX
    Explanations

    ein, ain, ayn, lain prefixes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    imetre
    0.41
    icoli
    0.38
     Bouchard
    0.38
     Nxf
    0.38
     आसार
    0.38
     ।”
    0.38
     थेट
    0.38
    薢
    0.38
    ";//
    0.38
    对比
    0.37
    POSITIVE LOGITS
     ain
    0.49
     Ain
    0.44
    Ein
    0.43
     nob
    0.43
    aint
    0.40
    从未
    0.40
     Ein
    0.40
     moment
    0.37
    蔷
    0.37
     einz
    0.37
    Act Density 0.003%

    No Known Activations