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

    Neuronpedia

    INDEX
    Explanations

    lack/lacks

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _FIN
    -0.08
    .Le
    -0.07
    aramel
    -0.07
    埃尔
    -0.07
     hablar
    -0.07
    进出口
    -0.07
    acio
    -0.06
    贝
    -0.06
    ,var
    -0.06
     slaves
    -0.06
    POSITIVE LOGITS
    TREE
    0.07
     Cemetery
    0.07
     jpg
    0.07
     Messiah
    0.07
    仅仅
    0.07
    _district
    0.07
     الدنيا
    0.07
    _DEBUG
    0.07
     clinically
    0.07
    的路上
    0.07
    Act Density 0.019%

    No Known Activations