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

    Neuronpedia

    INDEX
    Explanations

    loops

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    黠
    0.68
    undra
    0.63
    pea
    0.61
    anam
    0.60
     millimeters
    0.60
     Words
    0.60
     দেব
    0.59
     全
    0.59
     paralysie
    0.59
     देव
    0.59
    POSITIVE LOGITS
    while
    2.71
     while
    2.69
     WHILE
    2.58
     While
    2.33
     loops
    2.29
     loop
    2.28
    While
    2.27
     Loop
    2.14
    Loop
    2.07
     Loops
    2.03
    Act Density 0.356%

    No Known Activations