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

    Neuronpedia

    INDEX
    Explanations

    list items and descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     (
    0.60
     。
    0.50
     ("
    0.49
    。(
    0.48
     –
    0.47
     digraph
    0.47
    。（
    0.46
     quilt
    0.44
     terroir
    0.44
     san
    0.44
    POSITIVE LOGITS
    इस
    0.65
    the
    0.64
    The
    0.62
    !);
    0.61
    !!)
    0.59
    и
    0.58
    上記の
    0.57
    ی
    0.57
    च
    0.56
    ের
    0.55
    Act Density 0.228%

    No Known Activations