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

    Neuronpedia

    INDEX
    Explanations

    name

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Bare
    -0.06
     Prote
    -0.06
    LAS
    -0.06
     Thanksgiving
    -0.06
     Archae
    -0.06
    GAN
    -0.06
     private
    -0.06
    Ingrese
    -0.06
    ندق
    -0.05
     luckily
    -0.05
    POSITIVE LOGITS
     직접
    0.07
    .Directory
    0.07
    _Load
    0.07
     예정
    0.07
    sey
    0.06
     mem
    0.06
    职业
    0.06
     cabinet
    0.06
    营业
    0.06
     Settlement
    0.06
    Act Density 0.011%

    No Known Activations