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

    Neuronpedia

    INDEX
    Explanations

    international lines

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Amounts
    0.41
    綾
    0.37
    娯
    0.37
    Repeating
    0.37
    ToShow
    0.37
    User
    0.36
     מפ
    0.36
     مسلم
    0.36
    く
    0.35
     доходов
    0.35
    POSITIVE LOGITS
     pineapple
    0.42
     Pinch
    0.41
     angesch
    0.40
     polyurethane
    0.40
     Pineapple
    0.40
     Creations
    0.40
     downstairs
    0.39
    燔
    0.38
     squirrels
    0.38
     JP
    0.38
    Act Density 0.001%

    No Known Activations