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

    Neuronpedia

    INDEX
    Explanations

    causes or explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    পি
    0.40
     noirâtres
    0.40
     خلال
    0.38
    ರೆಯ
    0.38
    During
    0.37
    straße
    0.36
     آن‌ها
    0.36
    avorites
    0.35
    Background
    0.34
    ᅲ
    0.34
    POSITIVE LOGITS
     because
    0.57
     কারন
    0.52
     dont
    0.51
     Because
    0.49
     isnt
    0.49
     BECAUSE
    0.49
     doesnt
    0.49
     explot
    0.48
     wasnt
    0.47
     or
    0.47
    Act Density 0.000%

    No Known Activations