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

    Neuronpedia

    INDEX
    Explanations

    select object or one

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     tackle
    0.48
     حمله
    0.48
     Aprili
    0.45
    一
    0.45
     arah
    0.44
     soluzioni
    0.43
     ها
    0.43
     delicacy
    0.43
     Hail
    0.42
    ربي
    0.41
    POSITIVE LOGITS
    SELECT
    0.80
    Selective
    0.71
     selects
    0.69
    deselect
    0.69
    Select
    0.68
     Select
    0.68
    selecting
    0.66
     SELECT
    0.66
     selective
    0.64
     select
    0.63
    Act Density 0.014%

    No Known Activations