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

    Neuronpedia

    INDEX
    Explanations

    JSON documents

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    다
    0.53
    を
    0.45
     ইপিআর
    0.43
    ກ
    0.43
    ا
    0.42
    机器人
    0.41
    ؕ
    0.40
    ة
    0.40
    ṡ
    0.40
    льную
    0.39
    POSITIVE LOGITS
     Hemp
    0.46
     Holloway
    0.44
     Marlowe
    0.44
    恍
    0.43
     Frye
    0.43
     Clarke
    0.42
     タイプ
    0.42
    ftone
    0.42
     Lan
    0.41
     サングラス
    0.41
    Act Density 0.000%

    No Known Activations