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

    Neuronpedia

    INDEX
    Explanations

    Proper nouns/numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    AndEndTag
    -0.88
    SharedDtor
    -0.86
     Normdatei
    -0.81
     bezeichneter
    -0.69
    Santis
    -0.69
    خرى
    -0.68
     setCode
    -0.68
    TSCA
    -0.68
     سكانية
    -0.68
     senare
    -0.68
    POSITIVE LOGITS
    enumi
    0.54
    ########.
    0.48
    s
    0.48
    5
    0.44
    plo
    0.42
    udon
    0.40
    cu
    0.39
    mal
    0.38
    żym
    0.37
     п
    0.37
    Act Density 0.018%

    No Known Activations