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

    Neuronpedia

    INDEX
    Explanations

    comes from

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     الحال
    0.42
     meltdown
    0.41
     complication
    0.41
     attrition
    0.39
    ↠
    0.38
    padding
    0.38
     成分
    0.38
     conflict
    0.38
    Thickness
    0.38
     undocumented
    0.38
    POSITIVE LOGITS
    ດ້ວຍ
    0.42
     माइक्रोस
    0.38
    सेप्शन
    0.38
     нажмите
    0.37
     tampak
    0.37
    ouched
    0.36
     moż
    0.36
    hy
    0.35
     даст
    0.35
     रु
    0.35
    Act Density 0.000%

    No Known Activations