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

    Neuronpedia

    INDEX
    Explanations

    Affirmations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (userid
    -0.09
     kidn
    -0.09
     sau
    -0.08
    (short
    -0.08
     geraten
    -0.08
    Directory
    -0.08
     cierta
    -0.08
    (md
    -0.07
    (pic
    -0.07
    ())),↵
    -0.07
    POSITIVE LOGITS
     effortlessly
    0.10
    ✨
    0.09
     ನನ್ನ
    0.08
     �
    0.08
     ❤️
    0.08
     我
    0.08
     hustle
    0.08
     impulse
    0.08
    ✅
    0.08
     ✅
    0.08
    Act Density 0.008%

    No Known Activations