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

    Neuronpedia

    INDEX
    Explanations

    conjunctions and addition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    之所以
    0.47
    ческа
    0.43
     »
    0.42
     ,"
    0.39
     แรก
    0.39
    Paulo
    0.38
     ,'
    0.38
    .”)
    0.38
    ❞
    0.38
    㴌
    0.38
    POSITIVE LOGITS
     also
    0.62
     ALSO
    0.57
     additionally
    0.54
     simultaneously
    0.54
     zároveň
    0.51
     ayrıca
    0.51
    also
    0.49
     aussi
    0.49
    גם
    0.47
     myös
    0.47
    Act Density 0.009%

    No Known Activations