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

    Neuronpedia

    INDEX
    Explanations

    Atomic position/occupancy

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    196
    -0.07
     domingo
    -0.07
    Plans
    -0.06
     orderly
    -0.06
     enslaved
    -0.06
     reefs
    -0.06
    業
    -0.06
    -power
    -0.06
    power
    -0.06
    混
    -0.06
    POSITIVE LOGITS
    لیت
    0.06
    糖
    0.06
    一年
    0.06
     орг
    0.06
    /chat
    0.06
    κο
    0.06
    (config
    0.06
    WindowSize
    0.06
     Qgs
    0.06
     Rocket
    0.05
    Act Density 0.039%

    No Known Activations