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

    Neuronpedia

    INDEX
    Explanations

    children

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ΟΡ
    -0.06
     Norman
    -0.06
     timestamps
    -0.06
     bugün
    -0.06
     gates
    -0.06
    atoi
    -0.06
     warp
    -0.06
    dims
    -0.06
     amber
    -0.06
     persön
    -0.06
    POSITIVE LOGITS
     reinforces
    0.07
    ابط
    0.06
    .food
    0.06
    *ft
    0.06
         ↵↵
    0.06
    лед
    0.06
    )[
    0.06
    šetření
    0.06
     sneak
    0.06
    explo
    0.06
    Act Density 0.027%

    No Known Activations