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

    Neuronpedia

    INDEX
    Explanations

    For data analysis

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Silk
    0.37
     surpasses
    0.37
    尼
    0.36
     Aerial
    0.35
    এবং
    0.35
     Reserved
    0.34
     Berry
    0.34
    સભા
    0.33
     टुडे
    0.33
     CBS
    0.33
    POSITIVE LOGITS
    മായി
    0.39
    هِ
    0.37
     Го
    0.37
    രോധ
    0.36
     Mö
    0.36
    誠
    0.36
    കും
    0.35
     इंस्टीट
    0.35
    Sheikh
    0.34
     слоя
    0.34
    Act Density 1.384%

    No Known Activations