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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ANI
    -0.07
    жі
    -0.06
    pline
    -0.06
    けない
    -0.06
    -Za
    -0.06
    xdb
    -0.06
     correctly
    -0.06
    AS
    -0.06
    amb
    -0.06
     nhiều
    -0.06
    POSITIVE LOGITS
     중심
    0.07
     الجن
    0.07
     виход
    0.07
    ContextHolder
    0.06
    .Movie
    0.06
     bakım
    0.06
    บท
    0.06
     dém
    0.06
    .Automation
    0.06
    .Magenta
    0.06
    Act Density 0.042%

    No Known Activations