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

    Neuronpedia

    INDEX
    Explanations

    function calls and arguments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     lèvres
    0.18
     résult
    0.18
     stoichi
    0.18
     paralysie
    0.18
     molécule
    0.18
     言っ
    0.17
     удержи
    0.17
    GLAND
    0.17
     دارو
    0.17
     fistule
    0.17
    POSITIVE LOGITS
    false
    0.27
    null
    0.26
    5
    0.25
    new
    0.25
    2
    0.25
    3
    0.24
    open
    0.24
    4
    0.24
    create
    0.23
    let
    0.23
    Act Density 0.481%

    No Known Activations