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

    Neuronpedia

    INDEX
    Explanations

    Illuminate Support

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     giphy
    0.47
     dbo
    0.43
    Quadrant
    0.41
    授权
    0.40
     cityName
    0.38
     compounding
    0.37
    confidence
    0.37
    цтва
    0.37
    route
    0.37
     ৬৮
    0.37
    POSITIVE LOGITS
    Support
    0.78
     Support
    0.76
     support
    0.66
    支持
    0.56
     SUPPORT
    0.56
    support
    0.55
    SUPPORT
    0.54
     suport
    0.54
     Unterstützung
    0.52
    upport
    0.51
    Act Density 0.000%

    No Known Activations