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

    Neuronpedia

    INDEX
    Explanations

    X-UA-Compatible

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    他自己
    -0.67
    ђу
    -0.66
    Rie
    -0.66
    âmara
    -0.63
    ruecos
    -0.62
    chapel
    -0.62
     III
    -0.62
    COMPONENT
    -0.61
    읽
    -0.61
    fruit
    -0.60
    POSITIVE LOGITS
    macos
    0.71
    ёр
    0.71
    ISTE
    0.68
     Content
    0.68
     Contents
    0.67
    ۔۔
    0.67
     nanos
    0.67
    Content
    0.66
    getManager
    0.66
     brach
    0.66
    Act Density 0.049%

    No Known Activations