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

    Neuronpedia

    INDEX
    Explanations

    obtain, achieve, or decide

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Boris
    0.39
     Bord
    0.39
     Niko
    0.39
     Bulld
    0.38
    सर्जन
    0.38
    ⵔ
    0.37
     Baz
    0.36
     Apare
    0.36
     cts
    0.36
    cts
    0.36
    POSITIVE LOGITS
     취
    0.50
    取
    0.47
    취
    0.43
    㝡
    0.43
    דיה
    0.41
    に取り
    0.40
    ı
    0.39
    퇸
    0.39
    ้ง
    0.39
    舍
    0.38
    Act Density 0.002%

    No Known Activations