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

    Neuronpedia

    INDEX
    Explanations

    why

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     있는데
    -0.07
    actually
    -0.07
     그리고
    -0.07
     продукції
    -0.07
    。そして
    -0.07
     {
↵
↵
↵
    -0.06
    ipient
    -0.06
    обов
    -0.06
    ента
    -0.06
    งส
    -0.06
    POSITIVE LOGITS
    shi
    0.07
     athleticism
    0.07
    _filename
    0.07
     apparent
    0.06
    386
    0.06
    _pb
    0.06
     tokenizer
    0.06
     separators
    0.06
    εργ
    0.06
    Coord
    0.06
    Act Density 0.000%

    No Known Activations