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

    Neuronpedia

    INDEX
    Explanations

    Manufacturing processes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Separ
    -0.07
     auss
    -0.07
    <Self
    -0.07
     tarea
    -0.06
    atím
    -0.06
     fmt
    -0.06
     ска
    -0.06
     templates
    -0.06
     cev
    -0.06
     období
    -0.06
    POSITIVE LOGITS
    ้ง
    0.06
    (ROOT
    0.06
    gender
    0.06
    arking
    0.06
     prohibited
    0.06
    .BLUE
    0.06
     arsen
    0.06
     Fot
    0.06
    وق
    0.05
     ي
    0.05
    Act Density 0.063%

    No Known Activations