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

    Neuronpedia

    INDEX
    Explanations

    explaining `for i` loops

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    R
    0.68
      
    0.64
    O
    0.61
    amp
    0.60
    S
    0.60
     specifically
    0.60
    ens
    0.59
    H
    0.59
    D
    0.59
     R
    0.58
    POSITIVE LOGITS
    𒈨
    1.25
     버튼
    1.23
     betekent
    1.21
     $=\
    1.19
     означает
    1.18
    ();//
    1.18
     znači
    1.16
    ＝
    1.16
     contiene
    1.16
    ="";
    1.16
    Act Density 0.833%

    No Known Activations