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

    Neuronpedia

    INDEX
    Explanations

    binary

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Bruce
    -0.07
    صاب
    -0.07
    neh
    -0.06
    𝇜
    -0.06
    Locator
    -0.06
    㟁
    -0.06
     TOUCH
    -0.06
    侧结构性
    -0.06
    logs
    -0.06
     Phạm
    -0.06
    POSITIVE LOGITS
    씹
    0.06
    蝰
    0.06
    ')}↵
    0.06
    _ut
    0.06
    不间
    0.06
    蹩
    0.06
     <--
    0.06
    ToWorld
    0.06
    媄
    0.06
     hardened
    0.06
    Act Density 0.004%

    No Known Activations