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

    Neuronpedia

    INDEX
    Explanations

    DAR

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ropical
    -1.45
    MarshalTo
    -0.52
    OCCURRED
    -0.52
     yii
    -0.45
    EOUT
    -0.44
    }`).
    -0.43
    /*@
    -0.43
    onomía
    -0.43
    ության
    -0.43
    Jalan
    -0.40
    POSITIVE LOGITS
     تضيفلها
    1.06
     defaultstate
    0.71
     daglig
    0.64
    espół
    0.64
     profond
    0.62
    CompilerServices
    0.61
    edon
    0.60
    umumkan
    0.59
     חיצוניים
    0.57
     constater
    0.56
    Act Density 0.031%

    No Known Activations