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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     rebound
    -0.07
    する
    -0.07
     Address
    -0.07
     dressed
    -0.06
    izados
    -0.06
     helium
    -0.06
     Blender
    -0.06
     outlets
    -0.06
     Mod
    -0.06
     Management
    -0.06
    POSITIVE LOGITS
     gül
    0.08
    Tại
    0.07
    Franc
    0.06
     wang
    0.06
    调查
    0.06
     Executors
    0.06
     dés
    0.06
    ียรต
    0.06
    าคา
    0.06
    madığı
    0.06
    Act Density 0.250%

    No Known Activations