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

    Neuronpedia

    INDEX
    Explanations

    current position or state

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    otypes
    0.96
    方面的
    0.95
    ங்குகள்
    0.92
    ments
    0.92
    endas
    0.91
    们
    0.87
    EMENTS
    0.86
    aklar
    0.85
     futurs
    0.85
    ंजनों
    0.85
    POSITIVE LOGITS
    Position
    0.89
    값
    0.88
    Row
    0.86
    Item
    0.84
    Node
    0.84
    item
    0.81
     значення
    0.80
    value
    0.79
     item
    0.79
    CharCode
    0.77
    Act Density 0.156%

    No Known Activations