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

    Neuronpedia

    INDEX
    Explanations

    function definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     DR
    0.40
     GetAll
    0.38
     Novel
    0.36
     কূট
    0.36
    堪
    0.36
    ņa
    0.35
    erre
    0.35
     //!
    0.35
    άνει
    0.35
    aju
    0.35
    POSITIVE LOGITS
    cec
    0.45
     initialize
    0.44
    [](
    0.43
    initialize
    0.43
     innocuous
    0.42
     [](
    0.41
     successivement
    0.39
    ]=='
    0.39
    kfollowers
    0.39
     (…)
    0.38
    Act Density 0.001%

    No Known Activations