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

    Neuronpedia

    INDEX
    Explanations

    Natural language text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     حتی
    -0.07
     пара
    -0.06
     dici
    -0.06
     Costco
    -0.06
    REL
    -0.06
     carro
    -0.06
     Rou
    -0.06
    SEMB
    -0.06
    どう
    -0.06
     "{}
    -0.06
    POSITIVE LOGITS
     asp
    0.07
     FileName
    0.07
    ityEngine
    0.07
    .KeyPress
    0.07
    otional
    0.06
     priced
    0.06
     collect
    0.06
    览
    0.06
     nug
    0.06
     文件
    0.06
    Act Density 0.005%

    No Known Activations