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

    Neuronpedia

    INDEX
    Explanations

    excerpts of longer works

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Colorado
    -0.08
     Zion
    -0.07
     Dum
    -0.07
    GIN
    -0.07
    家伙
    -0.07
    轩辕
    -0.07
    预备
    -0.07
     Gaz
    -0.07
    eters
    -0.07
     Nem
    -0.06
    POSITIVE LOGITS
    .lineWidth
    0.08
    grid
    0.07
    lineno
    0.07
    -cat
    0.07
     gebru
    0.07
    third
    0.06
     التش
    0.06
     //{↵
    0.06
    (vector
    0.06
    lw
    0.06
    Act Density 0.067%

    No Known Activations