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

    Neuronpedia

    INDEX
    Explanations

    infrastructure concerns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     replied
    0.47
     inbox
    0.46
    饪
    0.44
     ہوگ
    0.43
    Reply
    0.41
    回复
    0.41
     Reply
    0.40
     brought
    0.40
    Email
    0.39
    étais
    0.39
    POSITIVE LOGITS
     pendapat
    0.42
     nicotin
    0.40
     Cyg
    0.39
    詬
    0.38
    浴
    0.38
     aversion
    0.38
     opinions
    0.37
     radiologists
    0.37
     निर्
    0.37
     cholesterol
    0.37
    Act Density 0.000%

    No Known Activations