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

    Neuronpedia

    INDEX
    Explanations

    Stories

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ỳ
    -0.07
    (rotation
    -0.07
    අ
    -0.07
     Curry
    -0.07
    (vm
    -0.06
    欧式
    -0.06
    캭
    -0.06
     Reese
    -0.06
    פה
    -0.06
     הולדת
    -0.06
    POSITIVE LOGITS
    抓住
    0.08
    펠
    0.07
    losures
    0.07
    閃
    0.07
    挡
    0.06
    責
    0.06
    休息
    0.06
     spill
    0.06
    кон
    0.06
    煽
    0.06
    Act Density 0.061%

    No Known Activations