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

    Neuronpedia

    INDEX
    Explanations

    fur and insulation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ك
    0.81
    იდ
    0.80
    م
    0.77
    韆
    0.67
    ف
    0.65
    était
    0.64
    gies
    0.63
    ка
    0.62
    ت
    0.62
    тта
    0.60
    POSITIVE LOGITS
     in
    0.68
     insulation
    0.68
    </b>
    0.67
     who
    0.63
     insulate
    0.63
    ↵
    0.62
     insulating
    0.62
     inter
    0.62
     hairy
    0.61
     drive
    0.61
    Act Density 0.011%

    No Known Activations