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

    Neuronpedia

    INDEX
    Explanations

    объектов, ободрение, абсолютное

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ↵
    1.54
    atan
    1.10
    ond
    1.05
    的相关
    1.05
    la
    1.04
    li
    1.02
    to
    1.01
     ป
    1.01
     realiz
    1.00
    の間
    1.00
    POSITIVE LOGITS
    f
    1.45
    ین
    1.44
    ні
    1.41
    ה
    1.40
    ק
    1.40
    v
    1.35
    in
    1.34
    ه
    1.28
    ও
    1.28
    지
    1.16
    Act Density 0.000%

    No Known Activations