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

    Neuronpedia

    INDEX
    Explanations

    maybe I think

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    非常に
    0.39
     нередко
    0.39
     특히
    0.38
     खासकर
    0.38
    你就
    0.38
    etc
    0.37
     Surprisingly
    0.37
     जोकि
    0.37
     অপেক্ষ
    0.36
    ikovsky
    0.36
    POSITIVE LOGITS
     chyba
    0.57
     možda
    0.45
     Creo
    0.44
    maybe
    0.44
     forse
    0.43
     maybe
    0.42
    Creo
    0.41
     misschien
    0.41
     MAY
    0.41
     glaube
    0.40
    Act Density 0.004%

    No Known Activations