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

    Neuronpedia

    INDEX
    Explanations

    definitions snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ند
    -0.08
    máticos
    -0.07
    Ł
    -0.07
    dur
    -0.07
    沃
    -0.07
    AffineTransform
    -0.07
     però
    -0.07
    getUser
    -0.07
    MARY
    -0.07
     André
    -0.07
    POSITIVE LOGITS
    窗户
    0.07
     skins
    0.07
    押金
    0.07
    說話
    0.07
    .Xr
    0.07
    hibition
    0.06
    他会
    0.06
    跨境电商
    0.06
     yg
    0.06
    leitung
    0.06
    Act Density 0.005%

    No Known Activations