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

    Neuronpedia

    INDEX
    Explanations

    >

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sequ
    -0.07
    You
    -0.06
     configs
    -0.06
     или
    -0.06
    (number
    -0.06
     آموز
    -0.06
    นๆ
    -0.06
    .Schema
    -0.06
     Lab
    -0.06
     exempl
    -0.06
    POSITIVE LOGITS
    formation
    0.07
    IR
    0.07
    紧
    0.07
    910
    0.06
     Wealth
    0.06
     brawl
    0.06
    	attack
    0.06
    preload
    0.06
     tetas
    0.06
    _asset
    0.06
    Act Density 0.001%

    No Known Activations