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

    Neuronpedia

    INDEX
    Explanations

    insurance discussions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sir
    0.39
     прису
    0.37
    はい
    0.37
    ohist
    0.35
    ஸில்
    0.34
    ➫
    0.34
    正しい
    0.34
     ILLUSTR
    0.33
    챔
    0.33
     ün
    0.33
    POSITIVE LOGITS
    insurance
    0.45
    Insurance
    0.45
    ियर्स
    0.44
     Insurance
    0.41
    uaire
    0.40
    yx
    0.39
    ুয়ারি
    0.39
    indicator
    0.39
    Completion
    0.38
    Head
    0.38
    Act Density 0.000%

    No Known Activations