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

    Neuronpedia

    INDEX
    Explanations

    decentralized

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    approval
    -0.07
    _unsigned
    -0.07
    pires
    -0.07
    _HIT
    -0.06
     vip
    -0.06
    יסה
    -0.06
     Trek
    -0.06
    ửa
    -0.06
    关键时刻
    -0.06
    :list
    -0.06
    POSITIVE LOGITS
     locally
    0.07
    ARG
    0.07
    ,self
    0.07
    MainMenu
    0.07
    陕
    0.07
     стала
    0.07
     Pods
    0.07
    โฮ
    0.07
    ........................
    0.07
    '),↵↵
    0.07
    Act Density 0.002%

    No Known Activations