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

    Neuronpedia

    INDEX
    Explanations

    (

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    lyn
    -0.07
    坳
    -0.07
     costumes
    -0.07
    ocytes
    -0.07
    着
    -0.06
    了一口气
    -0.06
    华盛顿
    -0.06
    倬
    -0.06
     TH
    -0.06
    cope
    -0.06
    POSITIVE LOGITS
    啤酒
    0.07
     Eternal
    0.07
    DataURL
    0.07
    ">&
    0.07
     Pied
    0.07
     字
    0.07
     Pack
    0.07
     selective
    0.06
     driven
    0.06
     Sample
    0.06
    Act Density 0.043%

    No Known Activations