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

    Neuronpedia

    INDEX
    Explanations

    areas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    2
    0.53
    phs
    0.44
    Holiday
    0.43
    omorphisms
    0.42
     Sessions
    0.42
    Session
    0.42
     SEM
    0.42
    般
    0.42
     Kaye
    0.42
    ⌘
    0.42
    POSITIVE LOGITS
    émique
    0.42
     sported
    0.42
     musul
    0.42
     vivienda
    0.41
     trasera
    0.41
     ಸ್ಥಾನ
    0.41
     країн
    0.41
     connecter
    0.41
    ンダ
    0.40
     exclusively
    0.40
    Act Density 0.006%

    No Known Activations