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

    Neuronpedia

    INDEX
    Explanations

    AI assistant identification

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    fault
    0.42
     literally
    0.39
    鍑
    0.38
    ৃত্বে
    0.37
     Geographical
    0.36
    ensa
    0.36
    ʿ
    0.36
    expired
    0.36
     गलती
    0.35
     ગો
    0.35
    POSITIVE LOGITS
    icone
    0.39
    kach
    0.36
     neod
    0.36
    ベージュ
    0.36
    ワン
    0.36
     याता
    0.36
    cone
    0.36
     Cous
    0.35
    万円
    0.35
     kolor
    0.35
    Act Density 0.003%

    No Known Activations