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

    Neuronpedia

    INDEX
    Explanations

    else blocks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ви
    1.30
    ಮಾಣ
    1.13
    มัน
    1.12
    слав
    1.04
     observables
    1.04
    𝐜
    1.04
    ouring
    1.02
     anhyd
    1.01
    ্লিকেশন
    1.01
     rozwiąz
    0.99
    POSITIVE LOGITS
    י
    1.72
    вання
    1.40
    ি
    1.39
    zelfde
    1.31
    ا
    1.29
    SON
    1.20
    ן
    1.20
    ছেন
    1.13
    い
    1.13
    서
    1.11
    Act Density 0.076%

    No Known Activations