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

    Neuronpedia

    INDEX
    Explanations

    always check / do

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    guardian
    0.48
    iculata
    0.43
    Human
    0.42
    णुओं
    0.42
    Rüyada
    0.42
    asked
    0.42
    پان
    0.42
    ᾶ
    0.42
    क्षकों
    0.41
    人間の
    0.41
    POSITIVE LOGITS
     ét
    0.53
     three
    0.48
     four
    0.48
     beagle
    0.47
     Navy
    0.46
     thé
    0.46
     étape
    0.45
     seulement
    0.45
    ්ර
    0.45
     American
    0.44
    Act Density 0.000%

    No Known Activations