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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     well
    0.33
    বর্ষ
    0.32
     Pest
    0.32
    翻
    0.32
     Kos
    0.31
     উপকরণ
    0.31
    Boris
    0.30
    medium
    0.30
     Preferences
    0.30
    备
    0.29
    POSITIVE LOGITS
    ificates
    0.31
     शेट्टी
    0.30
    ActionsCallback
    0.29
     четырех
    0.29
     négy
    0.29
    ∅
    0.28
    ivate
    0.28
     contou
    0.28
     iza
    0.28
    /**
    0.27
    Act Density 0.001%

    No Known Activations