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

    Neuronpedia

    INDEX
    Explanations

    because

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    يك
    1.20
    في
    1.05
    iiv
    1.03
     topologies
    1.02
    tails
    1.02
    ጠቀ
    1.02
    hre
    0.98
    ulence
    0.98
    hale
    0.98
    žila
    0.97
    POSITIVE LOGITS
    s
    1.22
    sk
    0.98
     싫
    0.97
    gies
    0.94
     reasons
    0.93
    ਂ
    0.93
    ్‌
    0.88
     детства
    0.88
     ◆
    0.87
    gie
    0.86
    Act Density 0.305%

    No Known Activations