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

    Neuronpedia

    INDEX
    Explanations

    for loop construct

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Dieses
    0.63
    Muchas
    0.61
     सामील
    0.55
     संघटना
    0.54
     लेणी
    0.54
     виды
    0.53
    Caractéristiques
    0.53
    بوون
    0.53
     चळ
    0.52
    Funeral
    0.51
    POSITIVE LOGITS
     i
    0.64
    suffix
    0.62
     L
    0.61
    hstack
    0.60
     T
    0.59
     In
    0.59
     d
    0.58
     kk
    0.57
     I
    0.57
    爣
    0.57
    Act Density 0.032%

    No Known Activations