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

    Neuronpedia

    INDEX
    Explanations

    html start tag

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ệt
    0.43
    虚拟机
    0.43
    駋
    0.42
    ipelago
    0.41
    ết
    0.41
     Debian
    0.40
     filesystem
    0.40
    <unused1011>
    0.39
    ి
    0.39
    isAssignableFrom
    0.39
    POSITIVE LOGITS
     штра
    0.45
     drunkenness
    0.40
    }$;
    0.40
    sufficiency
    0.39
     خلا
    0.38
     agua
    0.36
     உச்ச
    0.36
     torre
    0.36
     альтерна
    0.35
     agrad
    0.35
    Act Density 0.026%

    No Known Activations