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

    Neuronpedia

    INDEX
    Explanations

    past

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Prop
    -0.07
     Streams
    -0.06
    SO
    -0.06
     playoffs
    -0.06
    _ESCAPE
    -0.06
     purposes
    -0.06
    عکس
    -0.06
     bài
    -0.06
     gibi
    -0.06
    .Ac
    -0.06
    POSITIVE LOGITS
     =↵
    0.07
    료
    0.06
     Chí
    0.06
    _url
    0.06
    후기
    0.06
    .GetString
    0.06
    Ethernet
    0.06
     leer
    0.06
    -publish
    0.06
     arist
    0.06
    Act Density 0.026%

    No Known Activations