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

    Neuronpedia

    INDEX
    Explanations

    common word pairings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    /=
    0.48
    sw
    0.46
    يرا
    0.45
     bowel
    0.44
    with
    0.43
     wegen
    0.43
     selfless
    0.42
     been
    0.41
     دام
    0.41
     tumb
    0.40
    POSITIVE LOGITS
    必要があります
    0.66
     ERISA
    0.64
     Begriffe
    0.63
    <unused1930>
    0.63
     princípios
    0.62
    serrat
    0.62
     intéressant
    0.60
     질문
    0.60
     estudos
    0.60
    នុស្ស
    0.60
    Act Density 0.710%

    No Known Activations