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

    Neuronpedia

    INDEX
    Explanations

    measure

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ⎼
    -0.08
    .Components
    -0.07
    ⾛
    -0.07
    走在
    -0.07
     kho
    -0.07
    天国
    -0.07
    单项
    -0.07
    提供更多
    -0.06
    ỗ
    -0.06
    �
    -0.06
    POSITIVE LOGITS
     Prod
    0.08
     Может
    0.07
     cuatro
    0.07
    䣘
    0.06
    พฤศจ
    0.06
     Lug
    0.06
    (EX
    0.06
    _Project
    0.06
    'à
    0.06
    /Documents
    0.06
    Act Density 0.014%

    No Known Activations