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

    Neuronpedia

    INDEX
    Explanations

    factors and causes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    월
    0.63
    эг
    0.60
    AfterTax
    0.60
     använda
    0.59
    MyShop
    0.57
     ondas
    0.56
    SampleSize
    0.55
    foregroundView
    0.55
    %。
    0.54
    RIST
    0.54
    POSITIVE LOGITS
     endangering
    0.59
     complicating
    0.52
     compulsion
    0.50
    因素
    0.49
     inseparable
    0.49
     looming
    0.49
     determining
    0.48
     घटक
    0.48
     stoppage
    0.48
     являются
    0.48
    Act Density 0.379%

    No Known Activations