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

    Neuronpedia

    INDEX
    Explanations

    properly validating or preventing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     other
    0.55
     contradicts
    0.48
     calm
    0.47
     contradictions
    0.47
     ancak
    0.45
     despite
    0.45
     fakat
    0.44
     more
    0.44
     less
    0.44
     local
    0.44
    POSITIVE LOGITS
    ಶ್ಚ
    0.47
    áról
    0.46
     років
    0.44
    hasOwnProperty
    0.44
    籌
    0.44
     vært
    0.43
    ιού
    0.42
    ριά
    0.42
    мії
    0.42
     роки
    0.42
    Act Density 0.022%

    No Known Activations