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

    Neuronpedia

    INDEX
    Explanations

    AI models and comments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    maßnahmen
    -0.08
     Reise
    -0.08
     ರೀತ
    -0.08
     attrakt
    -0.08
     amat
    -0.08
     feststellen
    -0.08
     гара
    -0.08
     radius
    -0.08
     vad
    -0.08
     اقدامات
    -0.07
    POSITIVE LOGITS
     afges
    0.08
    (task
    0.08
     chatting
    0.07
     ignorant
    0.07
    (test
    0.07
    ALI
    0.07
     Casual
    0.07
    .tk
    0.07
     smoothies
    0.07
     tast
    0.07
    Act Density 0.005%

    No Known Activations