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

    Neuronpedia

    INDEX
    Explanations

    if clauses and variable access

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ⬮
    0.20
     bottlene
    0.19
     suppuration
    0.19
    𒊬
    0.19
    𒊏
    0.19
    鿢
    0.19
    BlockFit
    0.18
     Caedwalla
    0.18
    𒃻
    0.18
    𒊓
    0.18
    POSITIVE LOGITS
    0.28
      
    0.26
     (
    0.25
    int
    0.23
     "
    0.22
    i
    0.22
    (
    0.22
       
    0.21
    ((
    0.21
     '
    0.21
    Act Density 0.411%

    No Known Activations