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

    Neuronpedia

    INDEX
    Explanations

    override

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     مدرس
    0.43
    ⠈
    0.42
     капи
    0.42
     сами
    0.42
     Materialien
    0.41
     albums
    0.41
     AVENUE
    0.40
    ).]
    0.40
     أيام
    0.40
    \!
    0.39
    POSITIVE LOGITS
     override
    0.61
     overridden
    0.59
    Override
    0.56
     overriding
    0.55
     conflicting
    0.55
     prerog
    0.55
     Override
    0.53
     conflit
    0.53
    override
    0.52
    overwrite
    0.50
    Act Density 0.008%

    No Known Activations