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

    Neuronpedia

    INDEX
    Explanations

    explaining how or when

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     naam
    0.45
     hochwertige
    0.45
    elected
    0.44
     kvalit
    0.44
     listed
    0.42
     تحليل
    0.41
     methods
    0.41
     censoring
    0.41
     assemblies
    0.41
     nanop
    0.41
    POSITIVE LOGITS
     सल्
    0.48
    निया
    0.46
    inkin
    0.44
    尔多
    0.44
     auprès
    0.43
     Vega
    0.43
    Econom
    0.43
    antica
    0.43
    Ди
    0.43
     Atmos
    0.42
    Act Density 0.001%

    No Known Activations