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

    Neuronpedia

    INDEX
    Explanations

    function or state descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     variabile
    0.53
     vajj
    0.52
     mannequin
    0.50
     filesystem
    0.50
     estación
    0.50
    ತ್ರ
    0.49
     varieg
    0.49
    গামী
    0.49
     สวัสดี
    0.48
     variación
    0.48
    POSITIVE LOGITS
    0.49
    5
    0.44
     {
    0.43
     Lern
    0.42
     Klima
    0.42
    uk
    0.42
    (
    0.42
     Klim
    0.42
     Vent
    0.41
    0
    0.41
    Act Density 0.001%

    No Known Activations