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

    Neuronpedia

    INDEX
    Explanations

    Code/Programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     farewell
    -0.07
     Suites
    -0.06
    -disable
    -0.06
    .Delay
    -0.06
    :'↵
    -0.06
    _HEALTH
    -0.06
     lz
    -0.06
    国际
    -0.06
     qi
    -0.06
     Fro
    -0.06
    POSITIVE LOGITS
     climbing
    0.07
    ंस
    0.06
    .NODE
    0.06
    emoji
    0.06
    شناس
    0.06
    omination
    0.06
    .Cursor
    0.06
     subtype
    0.06
    _outputs
    0.06
    .RowStyle
    0.06
    Act Density 0.001%

    No Known Activations