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

    Neuronpedia

    INDEX
    Explanations

    arrays and lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     a
    1.10
    burger
    0.79
     to
    0.77
    lable
    0.77
    algia
    0.74
    coin
    0.71
    mongodb
    0.70
    ၡ
    0.70
    piece
    0.69
    pm
    0.68
    POSITIVE LOGITS
    ي
    1.18
    i
    1.02
    י
    0.93
    ে
    0.85
     elevationMap
    0.77
     numArray
    0.74
     gerenci
    0.74
     wordArray
    0.74
     automatis
    0.73
     совмести
    0.72
    Act Density 0.197%

    No Known Activations