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

    Neuronpedia

    INDEX
    Explanations

    varied text fragments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    됩니다
    -0.07
     ça
    -0.06
    “(
    -0.06
     getCategory
    -0.06
    Bi
    -0.06
    )!
    -0.06
     Juda
    -0.05
    Initialization
    -0.05
    gaard
    -0.05
    驱
    -0.05
    POSITIVE LOGITS
     els
    0.07
    .Render
    0.07
     aside
    0.07
    /compiler
    0.07
    tempts
    0.07
     treasure
    0.07
    	dst
    0.07
    .runners
    0.07
    figures
    0.06
     gam
    0.06
    Act Density 0.000%

    No Known Activations