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

    Neuronpedia

    INDEX
    Explanations

    兵马俑 and withColumn

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Encounter
    0.43
     Giving
    0.43
    にい
    0.40
    ..
    0.40
     ग्ला
    0.40
    เพื่อให้
    0.40
    onant
    0.39
     Especially
    0.38
    Oréal
    0.38
     برخ
    0.38
    POSITIVE LOGITS
     rapid
    0.42
    ется
    0.41
     fuel
    0.40
     quick
    0.38
     خودم
    0.37
     grit
    0.36
     katva
    0.36
    来源
    0.36
    我自己
    0.36
     CZ
    0.35
    Act Density 0.000%

    No Known Activations