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

    Neuronpedia

    INDEX
    Explanations

    incrementing loop counter `i`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Adding
    1.14
    Add
    1.00
    Continued
    0.93
    Continue
    0.92
    Next
    0.92
     adding
    0.91
    adding
    0.85
    More
    0.85
    Now
    0.83
    What
    0.82
    POSITIVE LOGITS
     ++
    1.01
    ︡
    0.90
     emblematic
    0.85
     especializada
    0.83
    ▭
    0.83
     ""){
    0.81
     banyak
    0.81
     jarang
    0.81
    খ
    0.80
     #-}
    0.80
    Act Density 0.024%

    No Known Activations