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

    Neuronpedia

    INDEX
    Explanations

    giving reasons or advice

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     initial
    0.42
     meaningful
    0.40
     Initial
    0.39
     displaced
    0.38
    न्द्रीय
    0.36
    oland
    0.36
     delivers
    0.35
    മ്പ
    0.35
    人士
    0.35
     Dye
    0.35
    POSITIVE LOGITS
     सीखने
    0.48
     মাত্র
    0.45
     REACTORS
    0.44
    près
    0.43
     weren
    0.43
     hỗ
    0.42
    😨
    0.42
     مدد
    0.42
    SGD
    0.42
     stöd
    0.42
    Act Density 0.003%

    No Known Activations