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

    Neuronpedia

    INDEX
    Explanations

    break down concepts or data

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     resulting
    0.52
     এমনকি
    0.52
     Malgré
    0.49
     alike
    0.47
    ዎችን
    0.46
    ഴിലാ
    0.45
    êtres
    0.45
    இதனால்
    0.45
     tandis
    0.44
    esimo
    0.44
    POSITIVE LOGITS
     Э
    0.55
     Jenis
    0.55
    㐄
    0.55
     урна
    0.53
    न्ति
    0.53
    tay
    0.51
     آهي
    0.50
     ہے
    0.49
     کیفیت
    0.49
    ግ
    0.49
    Act Density 0.072%

    No Known Activations