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

    Neuronpedia

    INDEX
    Explanations

    THEORY

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    蚊
    -0.07
    年轻
    -0.07
    Products
    -0.07
    rv
    -0.07
     crops
    -0.07
    unicode
    -0.07
     corpses
    -0.07
     crop
    -0.07
    点燃
    -0.07
    多样
    -0.06
    POSITIVE LOGITS
    ：↵↵
    0.07
    =Math
    0.07
    	actual
    0.07
    .CONFIG
    0.07
    tek
    0.07
    ớ
    0.07
     Preservation
    0.06
    켇
    0.06
     accountability
    0.06
    ":[{"
    0.06
    Act Density 0.001%

    No Known Activations