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

    Neuronpedia

    INDEX
    Explanations

    complex

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     indir
    -0.07
    .assertNot
    -0.07
     dışarı
    -0.07
     SER
    -0.07
    ARR
    -0.07
     bearer
    -0.07
     Nose
    -0.06
    arsing
    -0.06
     borrow
    -0.06
    -door
    -0.06
    POSITIVE LOGITS
     complexes
    0.08
     Complex
    0.08
     simplex
    0.08
    (Blueprint
    0.07
     complex
    0.07
    _analysis
    0.07
    wx
    0.07
     periodic
    0.07
    0.07
     Lucy
    0.07
    Act Density 0.015%

    No Known Activations