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

    Neuronpedia

    INDEX
    Explanations

    soft

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    =index
    -0.08
    西湖
    -0.07
     hive
    -0.07
     Hel
    -0.07
     spring
    -0.07
    뉩
    -0.07
    .sales
    -0.07
    installer
    -0.07
    conn
    -0.07
    ssue
    -0.07
    POSITIVE LOGITS
    TransparentColor
    0.09
     softer
    0.08
    gerät
    0.08
     soft
    0.08
     soaking
    0.07
    卡
    0.07
    ertos
    0.07
    工作机制
    0.07
     tortured
    0.07
     difíc
    0.07
    Act Density 0.016%

    No Known Activations