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

    Neuronpedia

    INDEX
    Explanations

    question or intro phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Pairing
    0.39
     उपलब्धि
    0.39
    Certainly
    0.38
     sellest
    0.36
    Pair
    0.36
     Rock
    0.35
    یعنی
    0.35
     unquestionably
    0.35
     undoubtedly
    0.35
    श्ती
    0.35
    POSITIVE LOGITS
    秅
    0.43
    主管部门
    0.42
    𝚞
    0.39
    шивания
    0.37
    正確
    0.36
     discapac
    0.35
    ฟา
    0.35
    usehen
    0.35
     coffees
    0.35
    筚
    0.35
    Act Density 0.000%

    No Known Activations