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

    Neuronpedia

    INDEX
    Explanations

    numerical values and parameters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    어요
    0.36
    ប៉ុ
    0.36
    arnell
    0.35
     небе
    0.35
     ಒಬ್ಬ
    0.35
    繃
    0.35
    EqualTo
    0.34
    قابل
    0.34
    থন
    0.33
    妑
    0.33
    POSITIVE LOGITS
     variables
    0.38
     placeholders
    0.36
     ২৫
    0.36
     اختيار
    0.36
    ২১
    0.35
    ২৭
    0.35
     प्रतिष्ठ
    0.34
     prose
    0.34
     ১৮
    0.33
    ২৫
    0.33
    Act Density 0.001%

    No Known Activations