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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     celle
    -0.08
     could
    -0.07
    six
    -0.07
     :,
    -0.07
    south
    -0.07
    这是因为
    -0.07
     Were
    -0.07
    thinking
    -0.06
     madre
    -0.06
    estado
    -0.06
    POSITIVE LOGITS
    “↵↵
    0.08
    鹰
    0.07
    鼠标
    0.07
     Proc
    0.07
    虎
    0.06
    `↵↵
    0.06
    特别
    0.06
     sho
    0.06
     Apache
    0.06
     التق
    0.06
    Act Density 0.049%

    No Known Activations