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

    Neuronpedia

    INDEX
    Explanations

    you do

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Doing
    0.99
    Doing
    0.94
     doing
    0.88
    ご
    0.85
    ပြု
    0.84
     ഉപയോഗ
    0.82
    邓
    0.82
     fazer
    0.78
     gøre
    0.77
     کرتے
    0.76
    POSITIVE LOGITS
     beliefs
    0.73
    though
    0.71
    less
    0.67
    also
    0.67
     principles
    0.65
    rafi
    0.64
     Vend
    0.64
     reasoning
    0.63
    eyse
    0.62
     term
    0.62
    Act Density 0.135%

    No Known Activations