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

    Neuronpedia

    INDEX
    Explanations

    specific computer terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     arrête
    0.53
    জ
    0.53
    ні
    0.52
     enunci
    0.50
     attain
    0.49
    aría
    0.49
     empat
    0.48
     auster
    0.48
    дә
    0.47
     exist
    0.46
    POSITIVE LOGITS
    3
    0.59
     لیے
    0.59
    _{
    0.57
    1
    0.56
    ibfk
    0.54
    -_
    0.54
    artige
    0.52
    4
    0.52
    akhir
    0.50
     تاريخ
    0.50
    Act Density 0.057%

    No Known Activations