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

    Neuronpedia

    INDEX
    Explanations

    numbers after phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     armazen
    0.91
    的な
    0.80
     Paribas
    0.80
     flog
    0.75
     коллек
    0.75
     przej
    0.74
     aliquot
    0.72
     seminal
    0.71
     этот
    0.71
    า
    0.71
    POSITIVE LOGITS
    n
    0.80
    🌊
    0.80
    ن
    0.79
    😈
    0.76
    ت
    0.75
    ĐT
    0.74
    orius
    0.73
    िं
    0.71
    сь
    0.70
    ون
    0.70
    Act Density 0.078%

    No Known Activations