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

    Neuronpedia

    INDEX
    Explanations

    example uses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Wright
    0.46
     Jesuit
    0.45
     aceste
    0.45
     Accordingly
    0.44
     día
    0.43
    Wright
    0.42
     zoos
    0.42
     queste
    0.41
     நினைவு
    0.41
     बिस्तर
    0.41
    POSITIVE LOGITS
    使用的是
    0.54
     utilizamos
    0.52
     sadece
    0.47
    简单的
    0.46
     Utilizamos
    0.46
    Assume
    0.45
     assumes
    0.45
    particular
    0.45
     utilisez
    0.44
    Example
    0.44
    Act Density 0.031%

    No Known Activations