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

    Neuronpedia

    INDEX
    Explanations

    consoles and logging in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hơn
    -0.07
    猷
    -0.07
     opc
    -0.07
    跄
    -0.06
    pliant
    -0.06
    餍
    -0.06
    罚
    -0.06
    ima
    -0.06
    亸
    -0.06
    粲
    -0.06
    POSITIVE LOGITS
    snake
    0.08
    _DAYS
    0.08
    𝓲
    0.07
    _ITEM
    0.07
    .Vertical
    0.07
     regiment
    0.07
    集團
    0.07
    建设工程
    0.07
     atomic
    0.07
    nızı
    0.07
    Act Density 0.015%

    No Known Activations