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

    Neuronpedia

    INDEX
    Explanations

    python and javascript docstrings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     return
    0.52
    ↵↵
    0.48
    ↵
    0.43
    stev
    0.42
    leave
    0.41
    arr
    0.40
    pag
    0.40
    $,
    0.40
    enem
    0.40
    gm
    0.39
    POSITIVE LOGITS
     Unlike
    0.52
    Unlike
    0.50
    Contrary
    0.50
     This
    0.49
    This
    0.48
    この
    0.48
     Contrary
    0.48
     ಇದು
    0.45
     этот
    0.45
     PLANNING
    0.45
    Act Density 0.012%

    No Known Activations