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

    Neuronpedia

    INDEX
    Explanations

    code and math

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    >*
    -0.06
    .ot
    -0.06
    .isfile
    -0.06
     Kids
    -0.06
    izzes
    -0.06
    очно
    -0.06
    dddd
    -0.06
     geen
    -0.06
    521
    -0.06
     ویر
    -0.06
    POSITIVE LOGITS
    .visual
    0.08
     propiedad
    0.07
    Memory
    0.07
    _environment
    0.06
    	border
    0.06
     plage
    0.06
    Dependency
    0.06
     buffers
    0.06
    壊
    0.06
    objet
    0.06
    Act Density 0.008%

    No Known Activations