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

    Neuronpedia

    INDEX
    Explanations

    Medicaid program details

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     of
    0.98
    ية
    0.94
     krä
    0.86
    kan
    0.85
    st
    0.82
    них
    0.82
     decentral
    0.80
    naire
    0.80
    ship
    0.76
    数百
    0.76
    POSITIVE LOGITS
    ו
    1.34
    ס
    1.30
    та
    0.98
    ל
    0.98
    ี
    0.96
    nimmt
    0.91
    :“
    0.87
    ,“
    0.86
     been
    0.85
     couches
    0.84
    Act Density 0.001%

    No Known Activations