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

    Neuronpedia

    INDEX
    Explanations

    Choose

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     vielleicht
    0.88
     perhaps
    0.85
     quizá
    0.84
     magari
    0.82
    perhaps
    0.82
     manchmal
    0.81
     talvez
    0.81
     maybe
    0.81
     misschien
    0.80
    既然
    0.79
    POSITIVE LOGITS
     Note
    1.57
    Note
    1.53
     note
    1.53
     NOTE
    1.41
    note
    1.31
    NOTE
    1.26
     PLEASE
    1.26
     **
    1.22
     remember
    1.11
    PLEASE
    1.09
    Act Density 0.790%

    No Known Activations