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

    Neuronpedia

    INDEX
    Explanations

    shared conversations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    郆
    0.45
    뤘
    0.44
     उन्‍होंने
    0.43
    눴
    0.43
     доставка
    0.42
    ၿ
    0.42
     vélo
    0.42
    りました
    0.41
    となりました
    0.41
    ؏
    0.41
    POSITIVE LOGITS
     FIG
    0.46
     preferably
    0.45
     hereinafter
    0.44
    FIG
    0.42
    preferably
    0.41
     wherein
    0.40
     relatively
    0.39
     plurality
    0.39
    benzoimidazole
    0.38
    plural
    0.38
    Act Density 0.002%

    No Known Activations