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

    Neuronpedia

    INDEX
    Explanations

    5**

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    擄
    0.39
     белорус
    0.38
     engagement
    0.38
    xin
    0.37
    ggio
    0.37
     Marche
    0.36
    شى
    0.35
    Engagement
    0.35
     queuing
    0.35
     Chac
    0.35
    POSITIVE LOGITS
    朼
    0.40
    interpret
    0.38
     interpretive
    0.38
    ómicos
    0.38
     interpret
    0.37
    skraft
    0.36
    圓
    0.36
     Brass
    0.36
     attainable
    0.36
     图片
    0.36
    Act Density 0.000%

    No Known Activations