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

    Neuronpedia

    INDEX
    Explanations

    introducing explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     दस
    0.43
     ход
    0.41
     diez
    0.39
     Examine
    0.39
     Grat
    0.37
    Ferguson
    0.36
     ten
    0.35
    レル
    0.35
    刨
    0.35
     Ferguson
    0.35
    POSITIVE LOGITS
     সেতুর
    0.37
    സ്വ
    0.36
    共有
    0.35
    ሼ
    0.35
    關於
    0.34
     ভারসাম
    0.34
     ज़रूरी
    0.34
     津
    0.33
     مختصر
    0.33
     condiv
    0.33
    Act Density 0.015%

    No Known Activations