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

    Neuronpedia

    INDEX
    Explanations

    customer and invoice data

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Stanley
    0.51
     Hannah
    0.43
     întreb
    0.43
     hamburg
    0.43
     incompre
    0.42
     laying
    0.42
    क्षा
    0.42
    0.41
     Whitney
    0.41
     аст
    0.41
    POSITIVE LOGITS
    cPix
    0.49
     بالط
    0.46
     контак
    0.46
     وف
    0.45
    𒂠
    0.45
    Defence
    0.45
    Billing
    0.43
    Behaviour
    0.43
    iciencies
    0.43
    adro
    0.43
    Act Density 0.001%

    No Known Activations