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

    Neuronpedia

    INDEX
    Explanations

    sequence or list items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     هنوز
    0.39
     bukanlah
    0.37
     পেয়েছে
    0.37
    ресенье
    0.37
    คัญ
    0.37
     shouldn
    0.36
     borne
    0.36
     repre
    0.36
    어야
    0.36
     berücksichtigt
    0.36
    POSITIVE LOGITS
    然后
    0.62
    然後
    0.62
     Then
    0.58
     затем
    0.58
    then
    0.55
     जब
    0.54
     then
    0.54
     When
    0.54
    Then
    0.54
     Each
    0.53
    Act Density 0.135%

    No Known Activations