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

    Neuronpedia

    INDEX
    Explanations

    want to describe or remember

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ocean
    0.48
    frame
    0.46
    ↵
    0.44
    js
    0.43
    client
    0.43
    app
    0.42
    fab
    0.42
    자
    0.42
    var
    0.42
    Signature
    0.41
    POSITIVE LOGITS
     uç
    0.54
     зи
    0.53
     представлены
    0.52
     провести
    0.51
     губерна
    0.50
    ле
    0.49
     çözüm
    0.47
     jaaye
    0.47
     lệ
    0.47
     президент
    0.46
    Act Density 0.002%

    No Known Activations