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

    Neuronpedia

    INDEX
    Explanations

    parsing text or data

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     whiteboard
    1.28
     Coventry
    1.24
     cheesecake
    1.20
     Vee
    1.18
     bitmaps
    1.17
     Bray
    1.16
    television
    1.16
     Speedway
    1.16
     Mino
    1.15
     Konrad
    1.14
    POSITIVE LOGITS
     Parsing
    1.45
     parsing
    1.28
    Parser
    1.25
     解析
    1.18
    parser
    1.18
     Parser
    1.18
    Parsing
    1.15
     args
    1.13
     parse
    1.11
    Pars
    1.10
    Act Density 0.698%

    No Known Activations