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

    Neuronpedia

    INDEX
    Explanations

    different

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    괴
    -0.08
     συγκ
    -0.08
     ಪರೀಕ್ಷ
    -0.08
     brauchen
    -0.08
     가지고
    -0.07
     Datei
    -0.07
     benötigen
    -0.07
    .Migrations
    -0.07
     Monitor
    -0.07
    .Get
    -0.07
    POSITIVE LOGITS
    thought
    0.09
    Thought
    0.08
     तरी
    0.08
     commentary
    0.08
    soever
    0.08
    שות
    0.08
    -eng
    0.08
    Whilst
    0.07
     stated
    0.07
     всеми
    0.07
    Act Density 0.008%

    No Known Activations