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

    Neuronpedia

    INDEX
    Explanations

    initialization and file handling

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    emoji
    0.39
    ញ្
    0.38
    বি
    0.36
    itational
    0.36
    understanding
    0.35
     виды
    0.34
     ಹೇಳ
    0.34
    నీ
    0.34
     viết
    0.34
    okhttp
    0.34
    POSITIVE LOGITS
     playthrough
    0.42
     batches
    0.38
    初期
    0.38
     Benutzer
    0.38
     carénés
    0.36
    複数の
    0.36
     initialization
    0.36
     individus
    0.36
     sayıda
    0.36
     初期
    0.36
    Act Density 0.242%

    No Known Activations