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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    伪装
    -0.07
    orry
    -0.07
    \File
    -0.07
     toán
    -0.07
     answers
    -0.07
     integrating
    -0.07
     hỏi
    -0.07
    纤维
    -0.07
     בני
    -0.06
    :,
    -0.06
    POSITIVE LOGITS
    (states
    0.08
     RIP
    0.07
     festivals
    0.07
     abide
    0.07
    くださ
    0.07
    rick
    0.07
     граф
    0.07
    aturated
    0.06
    ボード
    0.06
    Every
    0.06
    Act Density 0.041%

    No Known Activations