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

    Neuronpedia

    INDEX
    Explanations

    incrementing variables

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ########.
    -0.11
     Doll
    -0.09
     bol
    -0.09
    loo
    -0.09
    §Ãĥ
    -0.09
     Edison
    -0.09
    .GraphicsUnit
    -0.08
    äº
    -0.08
    IndexOf
    -0.08
    Sharper
    -0.08
    POSITIVE LOGITS
    1
    0.11
    erville
    0.10
    273
    0.09
    272
    0.09
    olina
    0.09
     alist
    0.09
    &
    0.08
    owed
    0.08
    ance
    0.08
    652
    0.08
    Act Density 0.018%

    No Known Activations