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

    Neuronpedia

    INDEX
    Explanations

    proving or detecting existence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     situate
    0.41
     [
    0.39
     myel
    0.39
     legitimately
    0.37
    дио
    0.37
     వివ
    0.37
    叮
    0.37
     necessity
    0.36
     مباشرة
    0.36
    ディレクトリ
    0.35
    POSITIVE LOGITS
    ania
    0.45
     مِن
    0.44
    sandwich
    0.41
    وسط
    0.39
    மணிய
    0.39
    ome
    0.39
     من
    0.39
    umer
    0.38
    وز
    0.38
    zio
    0.38
    Act Density 0.000%

    No Known Activations