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

    Neuronpedia

    INDEX
    Explanations

    DELLY

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    בק
    0.57
    ustomer
    0.54
    usermodel
    0.52
    layer
    0.50
    МА
    0.49
    InitTypeDef
    0.49
     idag
    0.49
    프트
    0.48
     camada
    0.48
     workflows
    0.48
    POSITIVE LOGITS
     เล่น
    0.61
     Serrurier
    0.55
     എന്നീ
    0.55
    জাত
    0.54
    其余
    0.53
    讲话
    0.53
     browned
    0.52
     Flies
    0.52
     तथा
    0.52
    нул
    0.52
    Act Density 0.875%

    No Known Activations