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

    Neuronpedia

    INDEX
    Explanations

    interior design

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    imende
    -0.08
     verband
    -0.08
    亿
    -0.08
     leswi
    -0.08
    emporary
    -0.08
     världen
    -0.08
     explic
    -0.07
     nuna
    -0.07
    この記事
    -0.07
     groundbreaking
    -0.07
    POSITIVE LOGITS
     focal
    0.08
    নের
    0.07
     দর
    0.07
    ivals
    0.07
    stretch
    0.07
     giriş
    0.07
     ори
    0.07
     turnkey
    0.07
     awkward
    0.07
     deductions
    0.07
    Act Density 0.025%

    No Known Activations