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

    Neuronpedia

    INDEX
    Explanations

    AI, persona, protection, security concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    atl
    0.50
    atá
    0.41
     surnames
    0.41
    truth
    0.41
    queue
    0.40
    ignores
    0.40
    컥
    0.39
    tolerance
    0.39
    byter
    0.38
    AO
    0.38
    POSITIVE LOGITS
     Anticip
    0.41
     Exposed
    0.41
     Indigo
    0.40
     Pats
    0.39
     Aujourd
    0.39
     Increase
    0.38
     Aut
    0.38
     oggi
    0.38
     Cour
    0.38
     View
    0.38
    Act Density 0.000%

    No Known Activations